Closed dapsjj closed 4 years ago
the network architecture should be consistent with the weights. I think you just loaded d2 weights into d0 network.
@zylo117 You are right,thanks!
@zylo117 You are right,thanks!
I made the same mistake, but My compound coef= 1 was set.
raceback (most recent call last):
File "efficientdet_test.py", line 62, in
I use this command to train custom dataset:
python train.py -c 2 -p curb --batch_size 2 --num_epochs 50 -w weights/efficientdet-d2.pth
There is only one class
curb
in my dataset. After 30 epochs,I stop training.Then I uselogs/curb/efficientdet-d2_21_10800.pth
to testefficientdet_test.py
,I usedobj_list = ['curb']
inefficientdet_test.py
,but the error message is:Traceback (most recent call last): File "E:/test/Yet-Another-EfficientDet-Pytorch-master/efficientdet_test.py", line 63, in model.load_state_dict(torch.load(r'weights/efficientdet-d2_21_10800.pth')) File "C:\Users\test\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 847, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for EfficientDetBackbone: Missing key(s) in state_dict: "backbone_net.model._blocks.1._expand_conv.conv.weight", "backbone_net.model._blocks.1._bn0.weight", "backbone_net.model._blocks.1._bn0.bias", "backbone_net.model._blocks.1._bn0.running_mean", "backbone_net.model._blocks.1._bn0.running_var". Unexpected key(s) in state_dict: "bifpn.3.p6_w1", "bifpn.3.p5_w1", "bifpn.3.p4_w1", "bifpn.3.p3_w1", "bifpn.3.p4_w2", "bifpn.3.p5_w2", "bifpn.3.p6_w2", "bifpn.3.p7_w2", "bifpn.3.conv6_up.depthwise_conv.conv.weight", "bifpn.3.conv6_up.pointwise_conv.conv.weight", "bifpn.3.conv6_up.pointwise_conv.conv.bias", "bifpn.3.conv6_up.bn.weight", "bifpn.3.conv6_up.bn.bias", "bifpn.3.conv6_up.bn.running_mean", "bifpn.3.conv6_up.bn.running_var", "bifpn.3.conv6_up.bn.num_batches_tracked", "bifpn.3.conv5_up.depthwise_conv.conv.weight", "bifpn.3.conv5_up.pointwise_conv.conv.weight", "bifpn.3.conv5_up.pointwise_conv.conv.bias", "bifpn.3.conv5_up.bn.weight", "bifpn.3.conv5_up.bn.bias", "bifpn.3.conv5_up.bn.running_mean", "bifpn.3.conv5_up.bn.running_var", "bifpn.3.conv5_up.bn.num_batches_tracked", "bifpn.3.conv4_up.depthwise_conv.conv.weight", "bifpn.3.conv4_up.pointwise_conv.conv.weight", "bifpn.3.conv4_up.pointwise_conv.conv.bias", "bifpn.3.conv4_up.bn.weight", "bifpn.3.conv4_up.bn.bias", "bifpn.3.conv4_up.bn.running_mean", "bifpn.3.conv4_up.bn.running_var", "bifpn.3.conv4_up.bn.num_batches_tracked", "bifpn.3.conv3_up.depthwise_conv.conv.weight", "bifpn.3.conv3_up.pointwise_conv.conv.weight", "bifpn.3.conv3_up.pointwise_conv.conv.bias", "bifpn.3.conv3_up.bn.weight", "bifpn.3.conv3_up.bn.bias", "bifpn.3.conv3_up.bn.running_mean", "bifpn.3.conv3_up.bn.running_var", "bifpn.3.conv3_up.bn.num_batches_tracked", "bifpn.3.conv4_down.depthwise_conv.conv.weight", "bifpn.3.conv4_down.pointwise_conv.conv.weight", "bifpn.3.conv4_down.pointwise_conv.conv.bias", "bifpn.3.conv4_down.bn.weight", "bifpn.3.conv4_down.bn.bias", "bifpn.3.conv4_down.bn.running_mean", "bifpn.3.conv4_down.bn.running_var", "bifpn.3.conv4_down.bn.num_batches_tracked", "bifpn.3.conv5_down.depthwise_conv.conv.weight", "bifpn.3.conv5_down.pointwise_conv.conv.weight", "bifpn.3.conv5_down.pointwise_conv.conv.bias", "bifpn.3.conv5_down.bn.weight", "bifpn.3.conv5_down.bn.bias", "bifpn.3.conv5_down.bn.running_mean", "bifpn.3.conv5_down.bn.running_var", "bifpn.3.conv5_down.bn.num_batches_tracked", "bifpn.3.conv6_down.depthwise_conv.conv.weight", "bifpn.3.conv6_down.pointwise_conv.conv.weight", "bifpn.3.conv6_down.pointwise_conv.conv.bias", "bifpn.3.conv6_down.bn.weight", "bifpn.3.conv6_down.bn.bias", "bifpn.3.conv6_down.bn.running_mean", "bifpn.3.conv6_down.bn.running_var", "bifpn.3.conv6_down.bn.num_batches_tracked", "bifpn.3.conv7_down.depthwise_conv.conv.weight", "bifpn.3.conv7_down.pointwise_conv.conv.weight", "bifpn.3.conv7_down.pointwise_conv.conv.bias", "bifpn.3.conv7_down.bn.weight", "bifpn.3.conv7_down.bn.bias", "bifpn.3.conv7_down.bn.running_mean", "bifpn.3.conv7_down.bn.running_var", "bifpn.3.conv7_down.bn.num_batches_tracked", "bifpn.4.p6_w1", "bifpn.4.p5_w1", "bifpn.4.p4_w1", "bifpn.4.p3_w1", "bifpn.4.p4_w2", "bifpn.4.p5_w2", "bifpn.4.p6_w2", "bifpn.4.p7_w2", "bifpn.4.conv6_up.depthwise_conv.conv.weight", "bifpn.4.conv6_up.pointwise_conv.conv.weight", "bifpn.4.conv6_up.pointwise_conv.conv.bias", "bifpn.4.conv6_up.bn.weight", "bifpn.4.conv6_up.bn.bias", "bifpn.4.conv6_up.bn.running_mean", "bifpn.4.conv6_up.bn.running_var", "bifpn.4.conv6_up.bn.num_batches_tracked", "bifpn.4.conv5_up.depthwise_conv.conv.weight", "bifpn.4.conv5_up.pointwise_conv.conv.weight", "bifpn.4.conv5_up.pointwise_conv.conv.bias", "bifpn.4.conv5_up.bn.weight", "bifpn.4.conv5_up.bn.bias", "bifpn.4.conv5_up.bn.running_mean", "bifpn.4.conv5_up.bn.running_var", "bifpn.4.conv5_up.bn.num_batches_tracked", "bifpn.4.conv4_up.depthwise_conv.conv.weight", "bifpn.4.conv4_up.pointwise_conv.conv.weight", "bifpn.4.conv4_up.pointwise_conv.conv.bias", "bifpn.4.conv4_up.bn.weight", "bifpn.4.conv4_up.bn.bias", "bifpn.4.conv4_up.bn.running_mean", "bifpn.4.conv4_up.bn.running_var", "bifpn.4.conv4_up.bn.num_batches_tracked", "bifpn.4.conv3_up.depthwise_conv.conv.weight", "bifpn.4.conv3_up.pointwise_conv.conv.weight", "bifpn.4.conv3_up.pointwise_conv.conv.bias", "bifpn.4.conv3_up.bn.weight", "bifpn.4.conv3_up.bn.bias", "bifpn.4.conv3_up.bn.running_mean", "bifpn.4.conv3_up.bn.running_var", "bifpn.4.conv3_up.bn.num_batches_tracked", "bifpn.4.conv4_down.depthwise_conv.conv.weight", "bifpn.4.conv4_down.pointwise_conv.conv.weight", "bifpn.4.conv4_down.pointwise_conv.conv.bias", "bifpn.4.conv4_down.bn.weight", "bifpn.4.conv4_down.bn.bias", "bifpn.4.conv4_down.bn.running_mean", "bifpn.4.conv4_down.bn.running_var", "bifpn.4.conv4_down.bn.num_batches_tracked", "bifpn.4.conv5_down.depthwise_conv.conv.weight", "bifpn.4.conv5_down.pointwise_conv.conv.weight", "bifpn.4.conv5_down.pointwise_conv.conv.bias", "bifpn.4.conv5_down.bn.weight", "bifpn.4.conv5_down.bn.bias", "bifpn.4.conv5_down.bn.running_mean", "bifpn.4.conv5_down.bn.running_var", "bifpn.4.conv5_down.bn.num_batches_tracked", "bifpn.4.conv6_down.depthwise_conv.conv.weight", "bifpn.4.conv6_down.pointwise_conv.conv.weight", "bifpn.4.conv6_down.pointwise_conv.conv.bias", "bifpn.4.conv6_down.bn.weight", "bifpn.4.conv6_down.bn.bias", "bifpn.4.conv6_down.bn.running_mean", "bifpn.4.conv6_down.bn.running_var", "bifpn.4.conv6_down.bn.num_batches_tracked", "bifpn.4.conv7_down.depthwise_conv.conv.weight", "bifpn.4.conv7_down.pointwise_conv.conv.weight", "bifpn.4.conv7_down.pointwise_conv.conv.bias", "bifpn.4.conv7_down.bn.weight", "bifpn.4.conv7_down.bn.bias", "bifpn.4.conv7_down.bn.running_mean", "bifpn.4.conv7_down.bn.running_var", "bifpn.4.conv7_down.bn.num_batches_tracked", "backbone_net.model._blocks.16._expand_conv.conv.weight", "backbone_net.model._blocks.16._bn0.weight", "backbone_net.model._blocks.16._bn0.bias", "backbone_net.model._blocks.16._bn0.running_mean", "backbone_net.model._blocks.16._bn0.running_var", "backbone_net.model._blocks.16._bn0.num_batches_tracked", "backbone_net.model._blocks.16._depthwise_conv.conv.weight", "backbone_net.model._blocks.16._bn1.weight", "backbone_net.model._blocks.16._bn1.bias", "backbone_net.model._blocks.16._bn1.running_mean", "backbone_net.model._blocks.16._bn1.running_var", "backbone_net.model._blocks.16._bn1.num_batches_tracked", "backbone_net.model._blocks.16._se_reduce.conv.weight", "backbone_net.model._blocks.16._se_reduce.conv.bias", "backbone_net.model._blocks.16._se_expand.conv.weight", "backbone_net.model._blocks.16._se_expand.conv.bias", "backbone_net.model._blocks.16._project_conv.conv.weight", "backbone_net.model._blocks.16._bn2.weight", "backbone_net.model._blocks.16._bn2.bias", "backbone_net.model._blocks.16._bn2.running_mean", "backbone_net.model._blocks.16._bn2.running_var", "backbone_net.model._blocks.16._bn2.num_batches_tracked", "backbone_net.model._blocks.17._expand_conv.conv.weight", "backbone_net.model._blocks.17._bn0.weight", "backbone_net.model._blocks.17._bn0.bias", "backbone_net.model._blocks.17._bn0.running_mean", "backbone_net.model._blocks.17._bn0.running_var", "backbone_net.model._blocks.17._bn0.num_batches_tracked", "backbone_net.model._blocks.17._depthwise_conv.conv.weight", "backbone_net.model._blocks.17._bn1.weight", "backbone_net.model._blocks.17._bn1.bias", "backbone_net.model._blocks.17._bn1.running_mean", "backbone_net.model._blocks.17._bn1.running_var", "backbone_net.model._blocks.17._bn1.num_batches_tracked", "backbone_net.model._blocks.17._se_reduce.conv.weight", "backbone_net.model._blocks.17._se_reduce.conv.bias", "backbone_net.model._blocks.17._se_expand.conv.weight", "backbone_net.model._blocks.17._se_expand.conv.bias", "backbone_net.model._blocks.17._project_conv.conv.weight", "backbone_net.model._blocks.17._bn2.weight", "backbone_net.model._blocks.17._bn2.bias", "backbone_net.model._blocks.17._bn2.running_mean", "backbone_net.model._blocks.17._bn2.running_var", "backbone_net.model._blocks.17._bn2.num_batches_tracked", "backbone_net.model._blocks.18._expand_conv.conv.weight", "backbone_net.model._blocks.18._bn0.weight", "backbone_net.model._blocks.18._bn0.bias", "backbone_net.model._blocks.18._bn0.running_mean", "backbone_net.model._blocks.18._bn0.running_var", "backbone_net.model._blocks.18._bn0.num_batches_tracked", "backbone_net.model._blocks.18._depthwise_conv.conv.weight", "backbone_net.model._blocks.18._bn1.weight", "backbone_net.model._blocks.18._bn1.bias", "backbone_net.model._blocks.18._bn1.running_mean", "backbone_net.model._blocks.18._bn1.running_var", "backbone_net.model._blocks.18._bn1.num_batches_tracked", "backbone_net.model._blocks.18._se_reduce.conv.weight", "backbone_net.model._blocks.18._se_reduce.conv.bias", "backbone_net.model._blocks.18._se_expand.conv.weight", "backbone_net.model._blocks.18._se_expand.conv.bias", "backbone_net.model._blocks.18._project_conv.conv.weight", "backbone_net.model._blocks.18._bn2.weight", "backbone_net.model._blocks.18._bn2.bias", "backbone_net.model._blocks.18._bn2.running_mean", "backbone_net.model._blocks.18._bn2.running_var", "backbone_net.model._blocks.18._bn2.num_batches_tracked", "backbone_net.model._blocks.19._expand_conv.conv.weight", "backbone_net.model._blocks.19._bn0.weight", "backbone_net.model._blocks.19._bn0.bias", "backbone_net.model._blocks.19._bn0.running_mean", "backbone_net.model._blocks.19._bn0.running_var", "backbone_net.model._blocks.19._bn0.num_batches_tracked", "backbone_net.model._blocks.19._depthwise_conv.conv.weight", "backbone_net.model._blocks.19._bn1.weight", "backbone_net.model._blocks.19._bn1.bias", "backbone_net.model._blocks.19._bn1.running_mean", "backbone_net.model._blocks.19._bn1.running_var", "backbone_net.model._blocks.19._bn1.num_batches_tracked", "backbone_net.model._blocks.19._se_reduce.conv.weight", "backbone_net.model._blocks.19._se_reduce.conv.bias", "backbone_net.model._blocks.19._se_expand.conv.weight", "backbone_net.model._blocks.19._se_expand.conv.bias", "backbone_net.model._blocks.19._project_conv.conv.weight", "backbone_net.model._blocks.19._bn2.weight", "backbone_net.model._blocks.19._bn2.bias", "backbone_net.model._blocks.19._bn2.running_mean", "backbone_net.model._blocks.19._bn2.running_var", "backbone_net.model._blocks.19._bn2.num_batches_tracked", "backbone_net.model._blocks.20._expand_conv.conv.weight", "backbone_net.model._blocks.20._bn0.weight", "backbone_net.model._blocks.20._bn0.bias", "backbone_net.model._blocks.20._bn0.running_mean", "backbone_net.model._blocks.20._bn0.running_var", "backbone_net.model._blocks.20._bn0.num_batches_tracked", "backbone_net.model._blocks.20._depthwise_conv.conv.weight", "backbone_net.model._blocks.20._bn1.weight", "backbone_net.model._blocks.20._bn1.bias", "backbone_net.model._blocks.20._bn1.running_mean", "backbone_net.model._blocks.20._bn1.running_var", "backbone_net.model._blocks.20._bn1.num_batches_tracked", "backbone_net.model._blocks.20._se_reduce.conv.weight", "backbone_net.model._blocks.20._se_reduce.conv.bias", "backbone_net.model._blocks.20._se_expand.conv.weight", "backbone_net.model._blocks.20._se_expand.conv.bias", "backbone_net.model._blocks.20._project_conv.conv.weight", "backbone_net.model._blocks.20._bn2.weight", "backbone_net.model._blocks.20._bn2.bias", "backbone_net.model._blocks.20._bn2.running_mean", "backbone_net.model._blocks.20._bn2.running_var", "backbone_net.model._blocks.20._bn2.num_batches_tracked", "backbone_net.model._blocks.21._expand_conv.conv.weight", "backbone_net.model._blocks.21._bn0.weight", "backbone_net.model._blocks.21._bn0.bias", "backbone_net.model._blocks.21._bn0.running_mean", "backbone_net.model._blocks.21._bn0.running_var", "backbone_net.model._blocks.21._bn0.num_batches_tracked", "backbone_net.model._blocks.21._depthwise_conv.conv.weight", "backbone_net.model._blocks.21._bn1.weight", "backbone_net.model._blocks.21._bn1.bias", "backbone_net.model._blocks.21._bn1.running_mean", "backbone_net.model._blocks.21._bn1.running_var", "backbone_net.model._blocks.21._bn1.num_batches_tracked", "backbone_net.model._blocks.21._se_reduce.conv.weight", "backbone_net.model._blocks.21._se_reduce.conv.bias", "backbone_net.model._blocks.21._se_expand.conv.weight", "backbone_net.model._blocks.21._se_expand.conv.bias", "backbone_net.model._blocks.21._project_conv.conv.weight", "backbone_net.model._blocks.21._bn2.weight", "backbone_net.model._blocks.21._bn2.bias", "backbone_net.model._blocks.21._bn2.running_mean", "backbone_net.model._blocks.21._bn2.running_var", "backbone_net.model._blocks.21._bn2.num_batches_tracked", "backbone_net.model._blocks.22._expand_conv.conv.weight", "backbone_net.model._blocks.22._bn0.weight", "backbone_net.model._blocks.22._bn0.bias", "backbone_net.model._blocks.22._bn0.running_mean", "backbone_net.model._blocks.22._bn0.running_var", "backbone_net.model._blocks.22._bn0.num_batches_tracked", "backbone_net.model._blocks.22._depthwise_conv.conv.weight", "backbone_net.model._blocks.22._bn1.weight", "backbone_net.model._blocks.22._bn1.bias", "backbone_net.model._blocks.22._bn1.running_mean", "backbone_net.model._blocks.22._bn1.running_var", "backbone_net.model._blocks.22._bn1.num_batches_tracked", "backbone_net.model._blocks.22._se_reduce.conv.weight", "backbone_net.model._blocks.22._se_reduce.conv.bias", "backbone_net.model._blocks.22._se_expand.conv.weight", "backbone_net.model._blocks.22._se_expand.conv.bias", "backbone_net.model._blocks.22._project_conv.conv.weight", "backbone_net.model._blocks.22._bn2.weight", "backbone_net.model._blocks.22._bn2.bias", "backbone_net.model._blocks.22._bn2.running_mean", "backbone_net.model._blocks.22._bn2.running_var", "backbone_net.model._blocks.22._bn2.num_batches_tracked". size mismatch for bifpn.0.conv6_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv6_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv6_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv5_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv5_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv4_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv4_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv3_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv3_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv3_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv3_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv3_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv3_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv3_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv4_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv4_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv4_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv5_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv5_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv5_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv6_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv6_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv6_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv7_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.0.conv7_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.0.conv7_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv7_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv7_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv7_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.conv7_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel.0.conv.weight: copying a param with shape torch.Size([112, 352, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 320, 1, 1]). size mismatch for bifpn.0.p5_down_channel.0.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel.0.conv.weight: copying a param with shape torch.Size([112, 120, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 112, 1, 1]). size mismatch for bifpn.0.p4_down_channel.0.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p3_down_channel.0.conv.weight: copying a param with shape torch.Size([112, 48, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 40, 1, 1]). size mismatch for bifpn.0.p3_down_channel.0.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p3_down_channel.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p3_down_channel.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p3_down_channel.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p3_down_channel.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_to_p6.0.conv.weight: copying a param with shape torch.Size([112, 352, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 320, 1, 1]). size mismatch for bifpn.0.p5_to_p6.0.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_to_p6.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_to_p6.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_to_p6.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_to_p6.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel_2.0.conv.weight: copying a param with shape torch.Size([112, 120, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 112, 1, 1]). size mismatch for bifpn.0.p4_down_channel_2.0.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel_2.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel_2.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel_2.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p4_down_channel_2.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel_2.0.conv.weight: copying a param with shape torch.Size([112, 352, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 320, 1, 1]). size mismatch for bifpn.0.p5_down_channel_2.0.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel_2.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel_2.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel_2.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.0.p5_down_channel_2.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv6_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv6_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv5_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv5_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv4_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv4_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv3_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv3_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv3_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv3_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv3_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv3_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv3_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv4_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv4_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv4_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv5_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv5_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv5_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv6_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv6_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv6_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv7_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.1.conv7_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.1.conv7_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv7_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv7_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv7_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.1.conv7_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv6_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv6_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv5_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv5_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv4_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv4_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv3_up.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv3_up.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv3_up.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv3_up.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv3_up.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv3_up.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv3_up.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv4_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv4_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv4_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv5_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv5_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv5_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv6_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv6_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv6_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv7_down.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for bifpn.2.conv7_down.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for bifpn.2.conv7_down.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv7_down.bn.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv7_down.bn.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv7_down.bn.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for bifpn.2.conv7_down.bn.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.conv_list.0.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for regressor.conv_list.0.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for regressor.conv_list.0.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.conv_list.1.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for regressor.conv_list.1.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for regressor.conv_list.1.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.conv_list.2.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for regressor.conv_list.2.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for regressor.conv_list.2.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.0.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.1.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.2.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.3.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.bn_list.4.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for regressor.header.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for regressor.header.pointwise_conv.conv.weight: copying a param with shape torch.Size([36, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([36, 64, 1, 1]). size mismatch for classifier.conv_list.0.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for classifier.conv_list.0.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for classifier.conv_list.0.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.conv_list.1.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for classifier.conv_list.1.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for classifier.conv_list.1.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.conv_list.2.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for classifier.conv_list.2.pointwise_conv.conv.weight: copying a param with shape torch.Size([112, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for classifier.conv_list.2.pointwise_conv.conv.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.0.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.1.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.2.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.3.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.0.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.0.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.0.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.0.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.1.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.1.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.1.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.1.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.2.weight: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.2.bias: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.2.running_mean: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.bn_list.4.2.running_var: copying a param with shape torch.Size([112]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for classifier.header.depthwise_conv.conv.weight: copying a param with shape torch.Size([112, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3]). size mismatch for classifier.header.pointwise_conv.conv.weight: copying a param with shape torch.Size([9, 112, 1, 1]) from checkpoint, the shape in current model is torch.Size([9, 64, 1, 1]). size mismatch for backbone_net.model._blocks.1._depthwise_conv.conv.weight: copying a param with shape torch.Size([16, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 1, 3, 3]). size mismatch for backbone_net.model._blocks.1._bn1.weight: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for backbone_net.model._blocks.1._bn1.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for backbone_net.model._blocks.1._bn1.running_mean: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for backbone_net.model._blocks.1._bn1.running_var: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for backbone_net.model._blocks.1._se_reduce.conv.weight: copying a param with shape torch.Size([4, 16, 1, 1]) from checkpoint, the shape in current model is torch.Size([4, 96, 1, 1]). size mismatch for backbone_net.model._blocks.1._se_expand.conv.weight: copying a param with shape torch.Size([16, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([96, 4, 1, 1]). size mismatch for backbone_net.model._blocks.1._se_expand.conv.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for backbone_net.model._blocks.1._project_conv.conv.weight: copying a param with shape torch.Size([16, 16, 1, 1]) from checkpoint, the shape in current model is torch.Size([24, 96, 1, 1]). size mismatch for backbone_net.model._blocks.1._bn2.weight: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([24]). size mismatch for backbone_net.model._blocks.1._bn2.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([24]). size mismatch for backbone_net.model._blocks.1._bn2.running_mean: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([24]). size mismatch for backbone_net.model._blocks.1._bn2.running_var: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([24]). size mismatch for backbone_net.model._blocks.2._expand_conv.conv.weight: copying a param with shape torch.Size([96, 16, 1, 1]) from checkpoint, the shape in current model is torch.Size([144, 24, 1, 1]). size mismatch for backbone_net.model._blocks.2._bn0.weight: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._bn0.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._bn0.running_mean: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._bn0.running_var: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._depthwise_conv.conv.weight: copying a param with shape torch.Size([96, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([144, 1, 3, 3]). size mismatch for backbone_net.model._blocks.2._bn1.weight: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._bn1.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._bn1.running_mean: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._bn1.running_var: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._se_reduce.conv.weight: copying a param with shape torch.Size([4, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([6, 144, 1, 1]). size mismatch for backbone_net.model._blocks.2._se_reduce.conv.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([6]). size mismatch for backbone_net.model._blocks.2._se_expand.conv.weight: copying a param with shape torch.Size([96, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([144, 6, 1, 1]). size mismatch for backbone_net.model._blocks.2._se_expand.conv.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([144]). size mismatch for backbone_net.model._blocks.2._project_conv.conv.weight: copying a param with shape torch.Size([24, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([24, 144, 1, 1]). size mismatch for backbone_net.model._blocks.3._depthwise_conv.conv.weight: copying a param with shape torch.Size([144, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([144, 1, 5, 5]). size mismatch for backbone_net.model._blocks.3._project_conv.conv.weight: copying a param with shape torch.Size([24, 144, 1, 1]) from checkpoint, the shape in current model is torch.Size([40, 144, 1, 1]). size mismatch for backbone_net.model._blocks.3._bn2.weight: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.3._bn2.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.3._bn2.running_mean: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.3._bn2.running_var: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.4._expand_conv.conv.weight: copying a param with shape torch.Size([144, 24, 1, 1]) from checkpoint, the shape in current model is torch.Size([240, 40, 1, 1]). size mismatch for backbone_net.model._blocks.4._bn0.weight: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._bn0.bias: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._bn0.running_mean: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._bn0.running_var: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._depthwise_conv.conv.weight: copying a param with shape torch.Size([144, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([240, 1, 5, 5]). size mismatch for backbone_net.model._blocks.4._bn1.weight: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._bn1.bias: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._bn1.running_mean: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._bn1.running_var: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._se_reduce.conv.weight: copying a param with shape torch.Size([6, 144, 1, 1]) from checkpoint, the shape in current model is torch.Size([10, 240, 1, 1]). size mismatch for backbone_net.model._blocks.4._se_reduce.conv.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([10]). size mismatch for backbone_net.model._blocks.4._se_expand.conv.weight: copying a param with shape torch.Size([144, 6, 1, 1]) from checkpoint, the shape in current model is torch.Size([240, 10, 1, 1]). size mismatch for backbone_net.model._blocks.4._se_expand.conv.bias: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.4._project_conv.conv.weight: copying a param with shape torch.Size([24, 144, 1, 1]) from checkpoint, the shape in current model is torch.Size([40, 240, 1, 1]). size mismatch for backbone_net.model._blocks.4._bn2.weight: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.4._bn2.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.4._bn2.running_mean: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.4._bn2.running_var: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([40]). size mismatch for backbone_net.model._blocks.5._expand_conv.conv.weight: copying a param with shape torch.Size([144, 24, 1, 1]) from checkpoint, the shape in current model is torch.Size([240, 40, 1, 1]). size mismatch for backbone_net.model._blocks.5._bn0.weight: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._bn0.bias: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._bn0.running_mean: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._bn0.running_var: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._depthwise_conv.conv.weight: copying a param with shape torch.Size([144, 1, 5, 5]) from checkpoint, the shape in current model is torch.Size([240, 1, 3, 3]). size mismatch for backbone_net.model._blocks.5._bn1.weight: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._bn1.bias: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._bn1.running_mean: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._bn1.running_var: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._se_reduce.conv.weight: copying a param with shape torch.Size([6, 144, 1, 1]) from checkpoint, the shape in current model is torch.Size([10, 240, 1, 1]). size mismatch for backbone_net.model._blocks.5._se_reduce.conv.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([10]). size mismatch for backbone_net.model._blocks.5._se_expand.conv.weight: copying a param with shape torch.Size([144, 6, 1, 1]) from checkpoint, the shape in current model is torch.Size([240, 10, 1, 1]). size mismatch for backbone_net.model._blocks.5._se_expand.conv.bias: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([240]). size mismatch for backbone_net.model._blocks.5._project_conv.conv.weight: copying a param with shape torch.Size([48, 144, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 240, 1, 1]). size mismatch for backbone_net.model._blocks.5._bn2.weight: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.5._bn2.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.5._bn2.running_mean: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.5._bn2.running_var: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.6._expand_conv.conv.weight: copying a param with shape torch.Size([288, 48, 1, 1]) from checkpoint, the shape in current model is torch.Size([480, 80, 1, 1]). size mismatch for backbone_net.model._blocks.6._bn0.weight: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._bn0.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._bn0.running_mean: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._bn0.running_var: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._depthwise_conv.conv.weight: copying a param with shape torch.Size([288, 1, 5, 5]) from checkpoint, the shape in current model is torch.Size([480, 1, 3, 3]). size mismatch for backbone_net.model._blocks.6._bn1.weight: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._bn1.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._bn1.running_mean: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._bn1.running_var: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._se_reduce.conv.weight: copying a param with shape torch.Size([12, 288, 1, 1]) from checkpoint, the shape in current model is torch.Size([20, 480, 1, 1]). size mismatch for backbone_net.model._blocks.6._se_reduce.conv.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([20]). size mismatch for backbone_net.model._blocks.6._se_expand.conv.weight: copying a param with shape torch.Size([288, 12, 1, 1]) from checkpoint, the shape in current model is torch.Size([480, 20, 1, 1]). size mismatch for backbone_net.model._blocks.6._se_expand.conv.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.6._project_conv.conv.weight: copying a param with shape torch.Size([48, 288, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 480, 1, 1]). size mismatch for backbone_net.model._blocks.6._bn2.weight: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.6._bn2.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.6._bn2.running_mean: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.6._bn2.running_var: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.7._expand_conv.conv.weight: copying a param with shape torch.Size([288, 48, 1, 1]) from checkpoint, the shape in current model is torch.Size([480, 80, 1, 1]). size mismatch for backbone_net.model._blocks.7._bn0.weight: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._bn0.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._bn0.running_mean: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._bn0.running_var: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._depthwise_conv.conv.weight: copying a param with shape torch.Size([288, 1, 5, 5]) from checkpoint, the shape in current model is torch.Size([480, 1, 3, 3]). size mismatch for backbone_net.model._blocks.7._bn1.weight: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._bn1.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._bn1.running_mean: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._bn1.running_var: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._se_reduce.conv.weight: copying a param with shape torch.Size([12, 288, 1, 1]) from checkpoint, the shape in current model is torch.Size([20, 480, 1, 1]). size mismatch for backbone_net.model._blocks.7._se_reduce.conv.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([20]). size mismatch for backbone_net.model._blocks.7._se_expand.conv.weight: copying a param with shape torch.Size([288, 12, 1, 1]) from checkpoint, the shape in current model is torch.Size([480, 20, 1, 1]). size mismatch for backbone_net.model._blocks.7._se_expand.conv.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.7._project_conv.conv.weight: copying a param with shape torch.Size([48, 288, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 480, 1, 1]). size mismatch for backbone_net.model._blocks.7._bn2.weight: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.7._bn2.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.7._bn2.running_mean: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.7._bn2.running_var: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([80]). size mismatch for backbone_net.model._blocks.8._expand_conv.conv.weight: copying a param with shape torch.Size([288, 48, 1, 1]) from checkpoint, the shape in current model is torch.Size([480, 80, 1, 1]). size mismatch for backbone_net.model._blocks.8._bn0.weight: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._bn0.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._bn0.running_mean: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._bn0.running_var: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._depthwise_conv.conv.weight: copying a param with shape torch.Size([288, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([480, 1, 5, 5]). size mismatch for backbone_net.model._blocks.8._bn1.weight: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._bn1.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._bn1.running_mean: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._bn1.running_var: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._se_reduce.conv.weight: copying a param with shape torch.Size([12, 288, 1, 1]) from checkpoint, the shape in current model is torch.Size([20, 480, 1, 1]). size mismatch for backbone_net.model._blocks.8._se_reduce.conv.bias: copying a param with shape torch.Size([12]) from checkpoint, the shape in current model is torch.Size([20]). size mismatch for backbone_net.model._blocks.8._se_expand.conv.weight: copying a param with shape torch.Size([288, 12, 1, 1]) from checkpoint, the shape in current model is torch.Size([480, 20, 1, 1]). size mismatch for backbone_net.model._blocks.8._se_expand.conv.bias: copying a param with shape torch.Size([288]) from checkpoint, the shape in current model is torch.Size([480]). size mismatch for backbone_net.model._blocks.8._project_conv.conv.weight: copying a param with shape torch.Size([88, 288, 1, 1]) from checkpoint, the shape in current model is torch.Size([112, 480, 1, 1]). size mismatch for backbone_net.model._blocks.8._bn2.weight: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.8._bn2.bias: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.8._bn2.running_mean: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.8._bn2.running_var: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.9._expand_conv.conv.weight: copying a param with shape torch.Size([528, 88, 1, 1]) from checkpoint, the shape in current model is torch.Size([672, 112, 1, 1]). size mismatch for backbone_net.model._blocks.9._bn0.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._bn0.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._bn0.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._bn0.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._depthwise_conv.conv.weight: copying a param with shape torch.Size([528, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([672, 1, 5, 5]). size mismatch for backbone_net.model._blocks.9._bn1.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._bn1.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._bn1.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._bn1.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._se_reduce.conv.weight: copying a param with shape torch.Size([22, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([28, 672, 1, 1]). size mismatch for backbone_net.model._blocks.9._se_reduce.conv.bias: copying a param with shape torch.Size([22]) from checkpoint, the shape in current model is torch.Size([28]). size mismatch for backbone_net.model._blocks.9._se_expand.conv.weight: copying a param with shape torch.Size([528, 22, 1, 1]) from checkpoint, the shape in current model is torch.Size([672, 28, 1, 1]). size mismatch for backbone_net.model._blocks.9._se_expand.conv.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.9._project_conv.conv.weight: copying a param with shape torch.Size([88, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([112, 672, 1, 1]). size mismatch for backbone_net.model._blocks.9._bn2.weight: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.9._bn2.bias: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.9._bn2.running_mean: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.9._bn2.running_var: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.10._expand_conv.conv.weight: copying a param with shape torch.Size([528, 88, 1, 1]) from checkpoint, the shape in current model is torch.Size([672, 112, 1, 1]). size mismatch for backbone_net.model._blocks.10._bn0.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._bn0.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._bn0.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._bn0.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._depthwise_conv.conv.weight: copying a param with shape torch.Size([528, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([672, 1, 5, 5]). size mismatch for backbone_net.model._blocks.10._bn1.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._bn1.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._bn1.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._bn1.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._se_reduce.conv.weight: copying a param with shape torch.Size([22, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([28, 672, 1, 1]). size mismatch for backbone_net.model._blocks.10._se_reduce.conv.bias: copying a param with shape torch.Size([22]) from checkpoint, the shape in current model is torch.Size([28]). size mismatch for backbone_net.model._blocks.10._se_expand.conv.weight: copying a param with shape torch.Size([528, 22, 1, 1]) from checkpoint, the shape in current model is torch.Size([672, 28, 1, 1]). size mismatch for backbone_net.model._blocks.10._se_expand.conv.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.10._project_conv.conv.weight: copying a param with shape torch.Size([88, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([112, 672, 1, 1]). size mismatch for backbone_net.model._blocks.10._bn2.weight: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.10._bn2.bias: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.10._bn2.running_mean: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.10._bn2.running_var: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([112]). size mismatch for backbone_net.model._blocks.11._expand_conv.conv.weight: copying a param with shape torch.Size([528, 88, 1, 1]) from checkpoint, the shape in current model is torch.Size([672, 112, 1, 1]). size mismatch for backbone_net.model._blocks.11._bn0.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._bn0.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._bn0.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._bn0.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._depthwise_conv.conv.weight: copying a param with shape torch.Size([528, 1, 3, 3]) from checkpoint, the shape in current model is torch.Size([672, 1, 5, 5]). size mismatch for backbone_net.model._blocks.11._bn1.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._bn1.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._bn1.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._bn1.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._se_reduce.conv.weight: copying a param with shape torch.Size([22, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([28, 672, 1, 1]). size mismatch for backbone_net.model._blocks.11._se_reduce.conv.bias: copying a param with shape torch.Size([22]) from checkpoint, the shape in current model is torch.Size([28]). size mismatch for backbone_net.model._blocks.11._se_expand.conv.weight: copying a param with shape torch.Size([528, 22, 1, 1]) from checkpoint, the shape in current model is torch.Size([672, 28, 1, 1]). size mismatch for backbone_net.model._blocks.11._se_expand.conv.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([672]). size mismatch for backbone_net.model._blocks.11._project_conv.conv.weight: copying a param with shape torch.Size([88, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 672, 1, 1]). size mismatch for backbone_net.model._blocks.11._bn2.weight: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.11._bn2.bias: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.11._bn2.running_mean: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.11._bn2.running_var: copying a param with shape torch.Size([88]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.12._expand_conv.conv.weight: copying a param with shape torch.Size([528, 88, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 192, 1, 1]). size mismatch for backbone_net.model._blocks.12._bn0.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._bn0.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._bn0.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._bn0.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._depthwise_conv.conv.weight: copying a param with shape torch.Size([528, 1, 5, 5]) from checkpoint, the shape in current model is torch.Size([1152, 1, 5, 5]). size mismatch for backbone_net.model._blocks.12._bn1.weight: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._bn1.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._bn1.running_mean: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._bn1.running_var: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._se_reduce.conv.weight: copying a param with shape torch.Size([22, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([48, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.12._se_reduce.conv.bias: copying a param with shape torch.Size([22]) from checkpoint, the shape in current model is torch.Size([48]). size mismatch for backbone_net.model._blocks.12._se_expand.conv.weight: copying a param with shape torch.Size([528, 22, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 48, 1, 1]). size mismatch for backbone_net.model._blocks.12._se_expand.conv.bias: copying a param with shape torch.Size([528]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.12._project_conv.conv.weight: copying a param with shape torch.Size([120, 528, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.12._bn2.weight: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.12._bn2.bias: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.12._bn2.running_mean: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.12._bn2.running_var: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.13._expand_conv.conv.weight: copying a param with shape torch.Size([720, 120, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 192, 1, 1]). size mismatch for backbone_net.model._blocks.13._bn0.weight: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._bn0.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._bn0.running_mean: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._bn0.running_var: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._depthwise_conv.conv.weight: copying a param with shape torch.Size([720, 1, 5, 5]) from checkpoint, the shape in current model is torch.Size([1152, 1, 5, 5]). size mismatch for backbone_net.model._blocks.13._bn1.weight: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._bn1.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._bn1.running_mean: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._bn1.running_var: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._se_reduce.conv.weight: copying a param with shape torch.Size([30, 720, 1, 1]) from checkpoint, the shape in current model is torch.Size([48, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.13._se_reduce.conv.bias: copying a param with shape torch.Size([30]) from checkpoint, the shape in current model is torch.Size([48]). size mismatch for backbone_net.model._blocks.13._se_expand.conv.weight: copying a param with shape torch.Size([720, 30, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 48, 1, 1]). size mismatch for backbone_net.model._blocks.13._se_expand.conv.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.13._project_conv.conv.weight: copying a param with shape torch.Size([120, 720, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.13._bn2.weight: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.13._bn2.bias: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.13._bn2.running_mean: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.13._bn2.running_var: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.14._expand_conv.conv.weight: copying a param with shape torch.Size([720, 120, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 192, 1, 1]). size mismatch for backbone_net.model._blocks.14._bn0.weight: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._bn0.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._bn0.running_mean: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._bn0.running_var: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._depthwise_conv.conv.weight: copying a param with shape torch.Size([720, 1, 5, 5]) from checkpoint, the shape in current model is torch.Size([1152, 1, 5, 5]). size mismatch for backbone_net.model._blocks.14._bn1.weight: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._bn1.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._bn1.running_mean: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._bn1.running_var: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._se_reduce.conv.weight: copying a param with shape torch.Size([30, 720, 1, 1]) from checkpoint, the shape in current model is torch.Size([48, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.14._se_reduce.conv.bias: copying a param with shape torch.Size([30]) from checkpoint, the shape in current model is torch.Size([48]). size mismatch for backbone_net.model._blocks.14._se_expand.conv.weight: copying a param with shape torch.Size([720, 30, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 48, 1, 1]). size mismatch for backbone_net.model._blocks.14._se_expand.conv.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.14._project_conv.conv.weight: copying a param with shape torch.Size([120, 720, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.14._bn2.weight: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.14._bn2.bias: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.14._bn2.running_mean: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.14._bn2.running_var: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for backbone_net.model._blocks.15._expand_conv.conv.weight: copying a param with shape torch.Size([720, 120, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 192, 1, 1]). size mismatch for backbone_net.model._blocks.15._bn0.weight: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._bn0.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._bn0.running_mean: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._bn0.running_var: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._depthwise_conv.conv.weight: copying a param with shape torch.Size([720, 1, 5, 5]) from checkpoint, the shape in current model is torch.Size([1152, 1, 3, 3]). size mismatch for backbone_net.model._blocks.15._bn1.weight: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._bn1.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._bn1.running_mean: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._bn1.running_var: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._se_reduce.conv.weight: copying a param with shape torch.Size([30, 720, 1, 1]) from checkpoint, the shape in current model is torch.Size([48, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.15._se_reduce.conv.bias: copying a param with shape torch.Size([30]) from checkpoint, the shape in current model is torch.Size([48]). size mismatch for backbone_net.model._blocks.15._se_expand.conv.weight: copying a param with shape torch.Size([720, 30, 1, 1]) from checkpoint, the shape in current model is torch.Size([1152, 48, 1, 1]). size mismatch for backbone_net.model._blocks.15._se_expand.conv.bias: copying a param with shape torch.Size([720]) from checkpoint, the shape in current model is torch.Size([1152]). size mismatch for backbone_net.model._blocks.15._project_conv.conv.weight: copying a param with shape torch.Size([120, 720, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 1152, 1, 1]). size mismatch for backbone_net.model._blocks.15._bn2.weight: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([320]). size mismatch for backbone_net.model._blocks.15._bn2.bias: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([320]). size mismatch for backbone_net.model._blocks.15._bn2.running_mean: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([320]). size mismatch for backbone_net.model._blocks.15._bn2.running_var: copying a param with shape torch.Size([120]) from checkpoint, the shape in current model is torch.Size([320]).
Can you tell me which parameter I changed? Thank you very much
i got the same error. And I find the model i have trained is also d2.pt,then i got the same error when i use efficientdet_test.py to verfiy my custom model. So how can i predict imgs with my custom d2.pt,which code shoud be changed ?
I use this command to train custom dataset:
python train.py -c 2 -p curb --batch_size 2 --num_epochs 50 -w weights/efficientdet-d2.pth
There is only one class
curb
in my dataset. After 30 epochs,I stop training.Then I uselogs/curb/efficientdet-d2_21_10800.pth
to testefficientdet_test.py
,I usedobj_list = ['curb']
inefficientdet_test.py
,but the error message is: