first I modified the main.py in
from networks.nnFormer.nnFormer_tumor import nnFormer
Traceback (most recent call last):
File "/home/wf/yf/3DUX-Net-main/main_train.py", line 600, in
global_step, dice_val_best, global_step_best = train(
File "/home/wf/yf/3DUX-Net-main/main_train.py", line 538, in train
loss = loss_function(logit_map, y)
File "/home/wf/anaconda3/envs/nnFormer0/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/wf/anaconda3/envs/nnFormer0/lib/python3.8/site-packages/monai/losses/dice.py", line 731, in forward
if len(input.shape) != len(target.shape):
AttributeError: 'list' object has no attribute 'shape'
so i modied -- loss = loss_function(logit_map[0], y)
TypeError: argmax(): argument 'input' (position 1) must be Tensor, not list
and UserWarning: For axis-0 of output[2], the output roi range is not int. Input roi range is (37, 133). Spatial zoom_scale between output[2] and input is 0.25. Corresponding output roi range is (9.25, 33.25).
Please change overlap (0.25) or roi_size (96) for axis-0. Tips: if overlaproi_sizezoom_scale is an integer, it usually works.
I'm not sure how to modify it again，I look forward to hearing from you!
first I modified the main.py in
global_step, dice_val_best, global_step_best = train(
File "/home/wf/yf/3DUX-Net-main/main_train.py", line 538, in train
loss = loss_function(logit_map, y)
File "/home/wf/anaconda3/envs/nnFormer0/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/wf/anaconda3/envs/nnFormer0/lib/python3.8/site-packages/monai/losses/dice.py", line 731, in forward
if len(input.shape) != len(target.shape):
AttributeError: 'list' object has no attribute 'shape'
from networks.nnFormer.nnFormer_tumor import nnFormer Traceback (most recent call last): File "/home/wf/yf/3DUX-Net-main/main_train.py", line 600, in
so i modied -- loss = loss_function(logit_map[0], y) TypeError: argmax(): argument 'input' (position 1) must be Tensor, not list and UserWarning: For axis-0 of output[2], the output roi range is not int. Input roi range is (37, 133). Spatial zoom_scale between output[2] and input is 0.25. Corresponding output roi range is (9.25, 33.25). Please change overlap (0.25) or roi_size (96) for axis-0. Tips: if overlaproi_sizezoom_scale is an integer, it usually works.
I'm not sure how to modify it again，I look forward to hearing from you!