uci-cbcl / NoduleNet

[MICCAI' 19] NoduleNet: Decoupled False Positive Reduction for Pulmonary Nodule Detection and Segmentation
Other
188 stars 58 forks source link

errors in segmentation network from 80 epochs #41

Closed scwuchung closed 2 years ago

scwuchung commented 2 years ago

when it come to 80 epochs , in the third step,80 epochs,the segmentation network start to work ,the follwing errros Traceback (most recent call last): File "train.py", line 428, in main() File "train.py", line 182, in main train(net, train_loader, optimizer, i, train_writer) File "train.py", line 220, in train net(input, truth_box, truth_label, truth_mask, masks) File "/home/chung/yes/envs/nodule/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, kwargs) File "/home/chung/Downloads/NoduleNet-master/net/nodule_net.py", line 414, in forward self.mask_probs = data_parallel(self.mask_head, (torch.from_numpy(self.crop_boxes).cuda(), features)) File "/home/chung/yes/envs/nodule/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 215, in data_parallel return module(*inputs[0], *module_kwargs[0]) File "/home/chung/yes/envs/nodule/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(input, kwargs) File "/home/chung/Downloads/NoduleNet-master/net/nodule_net.py", line 236, in forward up1 = f_4[b, :, z_start / 4:z_end / 4, y_start / 4:y_end / 4, x_start / 4:x_end / 4].unsqueeze(0) TypeError: only integer tensors of a single element can be converted to an index