a problems in the sampling process with BRATS2020 dataset

[liuweichenstart]

Traceback (most recent call last): File "scripts/segmentation_sample.py", line 191, in main() File "scripts/segmentation_sample.py", line 114, in main sample, x_noisy, org, cal, cal_out = sample_fn( File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/gaussian_diffusion.py", line 562, in p_sample_loop_known for sample in self.p_sample_loop_progressive( File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/gaussian_diffusion.py", line 647, in p_sample_loop_progressive out = self.p_sample( File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/gaussian_diffusion.py", line 442, in p_sample out = self.p_mean_variance( File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/respace.py", line 90, in p_mean_variance return super().p_mean_variance(self._wrap_model(model), *args, kwargs) File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/gaussian_diffusion.py", line 272, in p_mean_variance model_output = model(x, self._scale_timesteps(t), model_kwargs) File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/respace.py", line 135, in call return self.model(x, new_ts, kwargs) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/unet.py", line 1078, in forward anch, cal = self.highway_forward(c) File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/unet.py", line 1053, in highway_forward return self.hwm(x,hs = None) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/unet.py", line 2465, in forward x = self.conv_blocks_contextd File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/unet.py", line 2196, in forward return self.blocks(x) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/container.py", line 217, in forward input = module(input) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "/home/liuweichen/MedSegDiff-master_v2/./guided_diffusion/unet.py", line 2119, in forward x = self.conv(x) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 463, in forward return self._conv_forward(input, self.weight, self.bias) File "/home/liuweichen/anaconda3/envs/lwc/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 459, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: Given groups=1, weight of size [32, 4, 3, 3], expected input[1, 3, 256, 256] to have 4 channels, but got 3 channels instead

[WuJunde]

just as it reported, brats is supposed input a 4 channel data with ['t1', 't1ce', 't2', 'flair'], but not 3 channels

[liuweichenstart]

Thank you very much for taking the time to answer my questions. Based on your feedback, I ran the program again and found that the error results had changed. I am not very clear about this issue either.

------------------ 原始邮件 ------------------ 发件人: "WuJunde/MedSegDiff" @.>; 发送时间: 2023年5月25日(星期四) 晚上9:18 @.>; @.**@.>; 主题: Re: [WuJunde/MedSegDiff] a problems in the sampling process with BRATS2020 dataset (Issue #97)

just as it reported, brats is supposed input a 4 channel data with ['t1', 't1ce', 't2', 'flair'], but not 3 channels

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[WuJunde]

what's your error

[liuweichenstart]

------------------ 原始邮件 ------------------ 发件人: "WuJunde/MedSegDiff" @.>; 发送时间: 2023年5月29日(星期一) 中午11:12 @.>; @.**@.>; 主题: Re: [WuJunde/MedSegDiff] a problems in the sampling process with BRATS2020 dataset (Issue #97)

what's your error

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>