Traceback (most recent call last):
File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\train_fusion.py", line 713, in
main(args)
File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\train_fusion.py", line 349, in main
captuer = FeatureCapter(args, num_classes=args.num_classes)
File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\lib\model\fusion_Net.py", line 374, in init
self.strat_epoch_r, best_acc = load_checkpoint(self.Modalit_rgb, rgb_checkpoint)
File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\utils\utils.py", line 119, in load_checkpoint
model.load_state_dict(checkpoint['model'])
File "E:\anaconda\envs\mrgbd\lib\site-packages\torch\nn\modules\module.py", line 1497, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DSN:
size mismatch for SMS_layers.1.q.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.1.k.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.1.TM_project.0.weight: copying a param with shape torch.Size([64, 32]) from checkpoint, the shape in current model is torch.Size([32, 16]).
size mismatch for SMS_layers.1.TM_project.2.weight: copying a param with shape torch.Size([32, 64]) from checkpoint, the shape in current model is torch.Size([16, 32]).
size mismatch for SMS_layers.1.TM_project.3.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.1.TM_project.3.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.1.linear.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([512, 16]).
size mismatch for SMS_layers.3.q.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.3.k.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.3.TM_project.0.weight: copying a param with shape torch.Size([64, 32]) from checkpoint, the shape in current model is torch.Size([32, 16]).
size mismatch for SMS_layers.3.TM_project.2.weight: copying a param with shape torch.Size([32, 64]) from checkpoint, the shape in current model is torch.Size([16, 32]).
size mismatch for SMS_layers.3.TM_project.3.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.3.TM_project.3.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.3.linear.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([512, 16]).
size mismatch for SMS_layers.6.q.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.6.k.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.6.TM_project.0.weight: copying a param with shape torch.Size([64, 32]) from checkpoint, the shape in current model is torch.Size([32, 16]).
size mismatch for SMS_layers.6.TM_project.2.weight: copying a param with shape torch.Size([32, 64]) from checkpoint, the shape in current model is torch.Size([16, 32]).
size mismatch for SMS_layers.6.TM_project.3.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.6.TM_project.3.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.6.linear.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([512, 16]).
size mismatch for dtn.cls_tokens.0.pos_embedding: copying a param with shape torch.Size([1, 17, 512]) from checkpoint, the shape in current model is torch.Size([1, 9, 512]).
size mismatch for dtn.cls_tokens.1.pos_embedding: copying a param with shape torch.Size([1, 33, 512]) from checkpoint, the shape in current model is torch.Size([1, 17, 512]).
size mismatch for dtn.cls_tokens.2.pos_embedding: copying a param with shape torch.Size([1, 49, 512]) from checkpoint, the shape in current model is torch.Size([1, 25, 512]).
size mismatch for dtn.multi_scale_transformers.0.0.b1b.conv3d.weight: copying a param with shape torch.Size([224, 112, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([224, 112, 2, 1, 1]).
size mismatch for dtn.multi_scale_transformers.0.0.b2b.conv3d.weight: copying a param with shape torch.Size([64, 24, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 24, 2, 1, 1]).
size mismatch for dtn.multi_scale_transformers.1.0.b1b.conv3d.weight: copying a param with shape torch.Size([224, 112, 5, 1, 1]) from checkpoint, the shape in current model is torch.Size([224, 112, 4, 1, 1]).
size mismatch for dtn.multi_scale_transformers.1.0.b2b.conv3d.weight: copying a param with shape torch.Size([64, 24, 5, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 24, 4, 1, 1]).
size mismatch for dtn.multi_scale_transformers.2.0.b1b.conv3d.weight: copying a param with shape torch.Size([224, 112, 6, 1, 1]) from checkpoint, the shape in current model is torch.Size([224, 112, 4, 1, 1]).
size mismatch for dtn.multi_scale_transformers.2.0.b2b.conv3d.weight: copying a param with shape torch.Size([64, 24, 6, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 24, 4, 1, 1]).
Traceback (most recent call last): File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\train_fusion.py", line 713, in
main(args)
File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\train_fusion.py", line 349, in main
captuer = FeatureCapter(args, num_classes=args.num_classes)
File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\lib\model\fusion_Net.py", line 374, in init
self.strat_epoch_r, best_acc = load_checkpoint(self.Modalit_rgb, rgb_checkpoint)
File "G:\yanjiu\lunwen1\DUO\daima\MotionRGBD-PAMI-main\utils\utils.py", line 119, in load_checkpoint
model.load_state_dict(checkpoint['model'])
File "E:\anaconda\envs\mrgbd\lib\site-packages\torch\nn\modules\module.py", line 1497, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DSN:
size mismatch for SMS_layers.1.q.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.1.k.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.1.TM_project.0.weight: copying a param with shape torch.Size([64, 32]) from checkpoint, the shape in current model is torch.Size([32, 16]).
size mismatch for SMS_layers.1.TM_project.2.weight: copying a param with shape torch.Size([32, 64]) from checkpoint, the shape in current model is torch.Size([16, 32]).
size mismatch for SMS_layers.1.TM_project.3.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.1.TM_project.3.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.1.linear.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([512, 16]).
size mismatch for SMS_layers.3.q.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.3.k.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.3.TM_project.0.weight: copying a param with shape torch.Size([64, 32]) from checkpoint, the shape in current model is torch.Size([32, 16]).
size mismatch for SMS_layers.3.TM_project.2.weight: copying a param with shape torch.Size([32, 64]) from checkpoint, the shape in current model is torch.Size([16, 32]).
size mismatch for SMS_layers.3.TM_project.3.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.3.TM_project.3.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.3.linear.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([512, 16]).
size mismatch for SMS_layers.6.q.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.6.k.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([256, 16]).
size mismatch for SMS_layers.6.TM_project.0.weight: copying a param with shape torch.Size([64, 32]) from checkpoint, the shape in current model is torch.Size([32, 16]).
size mismatch for SMS_layers.6.TM_project.2.weight: copying a param with shape torch.Size([32, 64]) from checkpoint, the shape in current model is torch.Size([16, 32]).
size mismatch for SMS_layers.6.TM_project.3.weight: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.6.TM_project.3.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for SMS_layers.6.linear.weight: copying a param with shape torch.Size([512, 32]) from checkpoint, the shape in current model is torch.Size([512, 16]).
size mismatch for dtn.cls_tokens.0.pos_embedding: copying a param with shape torch.Size([1, 17, 512]) from checkpoint, the shape in current model is torch.Size([1, 9, 512]).
size mismatch for dtn.cls_tokens.1.pos_embedding: copying a param with shape torch.Size([1, 33, 512]) from checkpoint, the shape in current model is torch.Size([1, 17, 512]).
size mismatch for dtn.cls_tokens.2.pos_embedding: copying a param with shape torch.Size([1, 49, 512]) from checkpoint, the shape in current model is torch.Size([1, 25, 512]).
size mismatch for dtn.multi_scale_transformers.0.0.b1b.conv3d.weight: copying a param with shape torch.Size([224, 112, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([224, 112, 2, 1, 1]).
size mismatch for dtn.multi_scale_transformers.0.0.b2b.conv3d.weight: copying a param with shape torch.Size([64, 24, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 24, 2, 1, 1]).
size mismatch for dtn.multi_scale_transformers.1.0.b1b.conv3d.weight: copying a param with shape torch.Size([224, 112, 5, 1, 1]) from checkpoint, the shape in current model is torch.Size([224, 112, 4, 1, 1]).
size mismatch for dtn.multi_scale_transformers.1.0.b2b.conv3d.weight: copying a param with shape torch.Size([64, 24, 5, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 24, 4, 1, 1]).
size mismatch for dtn.multi_scale_transformers.2.0.b1b.conv3d.weight: copying a param with shape torch.Size([224, 112, 6, 1, 1]) from checkpoint, the shape in current model is torch.Size([224, 112, 4, 1, 1]).
size mismatch for dtn.multi_scale_transformers.2.0.b2b.conv3d.weight: copying a param with shape torch.Size([64, 24, 6, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 24, 4, 1, 1]).