HGCKL

a problrm in nodule_net.py

6

self.mask_probs = data_parallel(self.mask_head, (torch.from_numpy(self.crop_boxes).cuda(), features)) File "D:\anaconda\envs\Stest\lib\site-packages\torch\nn\parallel\data_parallel.py", line 231, in data_parallel return module(*inputs[0], **module_kwargs[0]) File "D:\anaconda\envs\Stest\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl return forward_call(*input, **kwargs) File "D:\HGQ_DL\NoduleNet\net\nodule_net.py", line 238, in forward up1...

你好，我按照你的代码执行良恶数据处理后训练后loss一直在0.5-0.6几震荡，增加了epoch和BN层以及去除数据增强都没有作用，请问你在LUNA2022中得到的训练结果图是执行的这个代码吗？

a problrm in nodule_net.py

2

File "D:\HGQ_DL\Nodule-CADx\src\net\nodule_net.py", line 420, in forward self.mask_probs = data_parallel(self.mask_head, (torch.from_numpy(self.crop_boxes).cuda(), features)) File "D:\anaconda\envs\Stest\lib\site-packages\torch\nn\parallel\data_parallel.py", line 231, in data_parallel return module(*inputs[0], **module_kwargs[0]) File "D:\anaconda\envs\Stest\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl return forward_call(*input, **kwargs) File...