RuntimeError: mat1 and mat2 shapes cannot be multiplied (200x117 and 29x3)

[Maritime-Moon]

E:\anaconda\envs\muren\python.exe E:\graduation\MUREN-master\main.py wandb: Currently logged in as: 1677607367 (1677607367-). Use wandb login --relogin to force relogin wandb: Appending key for api.wandb.ai to your netrc file: C:\Users\lenov/.netrc Not using distributed mode fatal: not a git repository (or any of the parent directories): .git git: sha: N/A, status: clean, branch: N/A

Namespace(alpha=0.5, aux_loss=True, backbone='resnet50', batch_size=2, bbox_loss_coef=2.5, clip_max_norm=0.1, dataset_file='vcoco', debug=False, dec_layers=6, device='cpu', dice_loss_coef=1, dilation=False, dim_feedforward=2048, dist_url='env://', distributed=False, dropout=0.1, enc_layers=6, eos_coef=0.1, epochs=100, eval=False, freeze=False, frozen_weights=None, gamma=0.1, giou_loss_coef=1, hidden_dim=256, hoi_path='E:/train data/data/v-coco', json_file='results.json', ko=False, lr=0.0001, lr_backbone=1e-05, lr_drop=60, mask_loss_coef=1, matching_loss_coef=1, nheads=8, nms_alpha=0.7, nms_beta=0.7, num_obj_classes=81, num_queries=100, num_verb_classes=117, num_workers=2, obj_loss_coef=1, output_dir='', position_embedding='sine', pre_norm=False, pretrained='pretrained/detr-r50-pre-2stage-nq100.pth', resume='', seed=42, set_cost_bbox=2.5, set_cost_class=1, set_cost_giou=1, set_cost_matching=1, set_cost_obj_class=1, set_cost_verb_class=1, start_epoch=0, subject_category_id=0, thres_nms=0.6, use_matching=False, use_nms_filter=False, verb_loss_coef=2, verb_loss_type='focal', weight_decay=0.0001, world_size=1) wandb: wandb version 0.18.1 is available! To upgrade, please run: wandb: $ pip install wandb --upgrade wandb: Tracking run with wandb version 0.14.2 wandb: Run data is saved locally in E:\graduation\MUREN-master\wandb\run-20240922_201603-kxjugp7f wandb: Run wandb offline to turn off syncing. wandb: Syncing run soft-hill-7 wandb: View project at https://wandb.ai/1677607367-/MUREN wandb: View run at https://wandb.ai/1677607367-/MUREN/runs/kxjugp7f Start training wandb: Currently logged in as: 1677607367 (1677607367-). Use wandb login --relogin to force relogin wandb: Appending key for api.wandb.ai to your netrc file: C:\Users\lenov/.netrc wandb: Currently logged in as: 1677607367 (1677607367-). Use wandb login --relogin to force relogin wandb: Appending key for api.wandb.ai to your netrc file: C:\Users\lenov/.netrc E:\anaconda\envs\muren\lib\site-packages\torch_tensor.py:575: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at ..\aten\src\ATen\native\BinaryOps.cpp:467.) return torch.floor_divide(self, other) Traceback (most recent call last): File "E:\graduation\MUREN-master\main.py", line 316, in main(args) File "E:\graduation\MUREN-master\main.py", line 246, in main args.clip_max_norm) File "E:\graduation\MUREN-master\engine.py", line 40, in train_one_epoch loss_dict = criterion(outputs, targets) File "E:\anaconda\envs\muren\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\graduation\MUREN-master\models\hoi.py", line 273, in forward indices = self.matcher(outputs_without_aux, targets) File "E:\anaconda\envs\muren\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\anaconda\envs\muren\lib\site-packages\torch\autograd\grad_mode.py", line 28, in decorate_context return func(*args, **kwargs) File "E:\graduation\MUREN-master\models\matcher.py", line 36, in forward cost_verb_class = -(out_verb_prob.matmul(tgt_verb_labels_permute) /
RuntimeError: mat1 and mat2 shapes cannot be multiplied (200x117 and 29x3) wandb: Waiting for W&B process to finish... (failed 1). Press Ctrl-C to abort syncing. wandb: View run soft-hill-7 at: https://wandb.ai/1677607367-/MUREN/runs/kxjugp7f wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s) wandb: Find logs at: .\wandb\run-20240922_201603-kxjugp7f\logs