monodetpht2 调试

1.出现调试尺寸问题

from future import absolute_import, division, print_function

Training
Traceback (most recent call last):
File “train.py”, line 18, in
trainer.train()
File “/home/lab316/Documents/Code/monodepth2/trainer.py”, line 186, in train
self.run_epoch()
File “/home/lab316/Documents/Code/monodepth2/trainer.py”, line 202, in run_epoch
outputs, losses = self.process_batch(inputs)
File “/home/lab316/Documents/Code/monodepth2/trainer.py”, line 245, in process_batch
features = self.models[“encoder”](inputs[“color_aug”, 0, 0])
File “/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py”, line 547, in call
result = self.forward(*input, **kwargs)
File “/home/lab316/Documents/Code/monodepth2/networks/resnet_encoder.py”, line 270, in forward
self.features.append(self.encoder.layer2(self.features[-1]))
File “/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py”, line 547, in call
result = self.forward(*input, **kwargs)
File “/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py”, line 92, in forward
input = module(input)
File “/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py”, line 547, in call
result = self.forward(*input, **kwargs)
File “/home/lab316/Documents/Code/monodepth2/networks/resnet_encoder.py”, line 140, in forward
out += residual
RuntimeError: The size of tensor a (80) must match the size of tensor b (40) at non-singleton dimension 3
这个问题去掉 absolute_import