主干跟换后报错

[chen-del]

主干跟换后出现了如下报错： Epoch 1/130: 0%| | 0/1439 [00:00<?, ?it/s<class 'dict'>]Traceback (most recent call last): File "train.py", line 527, in epoch_step, epoch_step_val, gen, gen_val, UnFreeze_Epoch, Cuda, dice_loss, focal_loss, cls_weights, aux_branch, num_classes, fp16, scaler, save_period, save_dir, local_rank) File "/home/dell/bag-torch/darkpull/Paddle/mmsegmentation/pspnet_torch/utils/utils_fit.py", line 64, in fit_one_epoch outputs = model_train(imgs) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 165, in forward return self.module(*inputs[0], **kwargs[0]) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/dell/bag-torch/darkpull/Paddle/mmsegmentation/pspnet_torch/nets/pspnet.py", line 308, in forward output = self.master_branch(x) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/container.py", line 119, in forward input = module(input) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/dell/bag-torch/darkpull/Paddle/mmsegmentation/pspnet_torch/nets/pspnet.py", line 234, in forward pyramids.extend([F.interpolate(stage(features), size=(h, w), mode='bilinear', align_corners=True) for stage in self.stages]) File "/home/dell/bag-torch/darkpull/Paddle/mmsegmentation/pspnet_torch/nets/pspnet.py", line 234, in pyramids.extend([F.interpolate(stage(features), size=(h, w), mode='bilinear', align_corners=True) for stage in self.stages]) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/container.py", line 119, in forward input = module(input) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/torch/nn/modules/pooling.py", line 616, in forward self.padding, self.ceil_mode, self.count_include_pad, self.divisor_override) RuntimeError: Given input size: (1280x1x1). Calculated output size: (1280x0x0). Output size is too small Epoch 1/130: 0%|