search

dbolya / yolact

A simple, fully convolutional model for real-time instance segmentation.
MIT License
5.03k stars 1.32k forks source link

RuntimeError: Error(s) in loading state_dict for Yolact: size mismatch for prediction_layers.0.conf_layer.weight: #577

Open DEncounter opened 3 years ago

DEncounter commented 3 years ago

Scaling parameters by 0.50 to account for a batch size of 4. Per-GPU batch size is less than the recommended limit for batch norm. Disabling batch norm. loading annotations into memory... Done (t=0.01s) creating index... index created! loading annotations into memory... Done (t=0.00s) creating index... index created! Resuming training, loading weights/yolact_base_54_800000.pth... Traceback (most recent call last): File "train.py", line 504, in train() File "train.py", line 207, in train yolact_net.load_weights(args.resume) File "/home/md/PycharmProjects/yolact-master/yolact.py", line 494, in load_weights self.load_state_dict(state_dict) File "/home/md/anaconda3/envs/pytorch1.2/lib/python3.6/site-packages/torch/nn/modules/module.py", line 845, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for Yolact: size mismatch for prediction_layers.0.conf_layer.weight: copying a param with shape torch.Size([243, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([6, 256, 3, 3]). size mismatch for prediction_layers.0.conf_layer.bias: copying a param with shape torch.Size([243]) from checkpoint, the shape in current model is torch.Size([6]). size mismatch for semantic_seg_conv.weight: copying a param with shape torch.Size([80, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 256, 1, 1]). size mismatch for semantic_seg_conv.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([1]).

NTS-wen commented 3 years ago

i have the same question.

Ultraopxt commented 3 years ago

i have the same question.

overman1 commented 3 years ago

i have the same question to use pretrained model

NTS-wen commented 3 years ago

You can fine the issue with the title of "Fine tuning with existing model" and your question will be resolved.

At 2021-04-29 17:20:01, "overman1" @.***> wrote:

i have the same question to use pretrained model

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.