RuntimeError: Error(s) in loading state_dict for FasterRCNN

1

I’m getting an error when i try to make predicts for my FasterRCNN object detection model. I was able to make predicts with same model file 2 days ago. But it gives error now.

Error:

RuntimeError: Error(s) in loading state_dict for FasterRCNN:
        size mismatch for roi_heads.box_predictor.cls_score.weight: copying a param with shape torch.Size([6, 1024]) from checkpoint, the shape in current model is torch.Size([13, 1024]).
        size mismatch for roi_heads.box_predictor.cls_score.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([13]).
        size mismatch for roi_heads.box_predictor.bbox_pred.weight: copying a param with shape torch.Size([24, 1024]) from checkpoint, the shape in current model is torch.Size([52, 1024]).
        size mismatch for roi_heads.box_predictor.bbox_pred.bias: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([52]).

Code from test.py:

# load the best model and trained weights
model = create_model(num_classes=NUM_CLASSES)
checkpoint = torch.load('C:\\Users\\lemon\\Desktop\\outputs_first\\last_model.pth', map_location=DEVICE)
model.load_state_dict(checkpoint['model_state_dict'])
model.to(DEVICE).eval()
2

The model you created has 13 classes where the state_dict you loaded has 6.

You should make them same.

1 Like
3

Ohhhh i got it now, i was just changed dataset so it has 13 classes. I missed it. Thank you so much!