backbone.bottom_up.res2.0.conv1.weight when using out_dir_r101/syn_model/model_syn_r101_pretrain.pth

[bschembri-UoM]

Hello,

I am getting a long list of lines similar to the below when using ./configs/ocr/synthtext_pretrain_101_FPN.yaml and model ./out_dir_r101/syn_model/model_syn_r101_pretrain.pth

'backbone.bottom_up.res2.0.conv1.weight' has shape (256, 64, 1, 1) in the checkpoint but (64, 64, 1, 1) in the model! Skipped. 'backbone.bottom_up.res2.0.conv1.norm.weight' has shape (256,) in the checkpoint but (64,) in the model! Skipped. 'backbone.bottom_up.res2.0.conv1.norm.bias' has shape (256,) in the checkpoint but (64,) in the model! Skipped. 'backbone.bottom_up.res2.0.conv1.norm.running_mean' has shape (256,) in the checkpoint but (64,) in the model! Skipped. " " a lot of other lines like the above... " File "/home/bschembri/VisionAssignment/predictor.py", line 48, in run_on_image predictions = self.predictor(image) File "/home/bschembri/anaconda3/envs/textfusenet2/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 49, in decorate_no_grad return func(*args, **kwargs) File "/home/bschembri/TextFuseNet/detectron2/engine/defaults.py", line 178, in call height, width = original_image.shape[:2] AttributeError: 'NoneType' object has no attribute 'shape'

Can you advise why this is happening and how can I fix it?

Thank you

[LIYHUI]

hi, I have also meet this problem? Have you solved it?