This net need fixed size image as input?

[binzhangbin]

Traceback (most recent call last): File "train.py", line 140, in output = model(X_batch) File "/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axialnet.py", line 507, in forward return self._forward_impl(x) File "/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axialnet.py", line 485, in _forward_impl x1 = self.layer1(x) File "/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules/container.py", line 139, in forward input = module(input) File "/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axialnet.py", line 331, in forward out = self.hight_block(out) File "/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axialnet.py", line 157, in forward qr = torch.einsum('bgci,cij->bgij', q, q_embedding) File "/home/zzp/.local/lib/python3.8/site-packages/torch/functional.py", line 299, in einsum return _VF.einsum(equation, operands) # type: ignore[attr-defined] RuntimeError: einsum(): operands do not broadcast with remapped shapes [original->remapped]: [2000, 8, 1, 500]->[2000, 8, 500, 1, 1] [1, 64, 64]->[1, 1, 64, 64, 1]

[wuyangzz]

你的问题解决了嘛。我也遇到了同样的问题。

[Hypothesisl]

你的问题解决了嘛。我也遇到了同样的问题。

i got the same, how's going

[huanqingxu]

i got the same, how's going

[huanqingxu]

qr = np.einsum('bgci,cij->bgij', q, q_embedding) File "<array_function internals>", line 6, in einsum File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/numpy/core/einsumfunc.py", line 1356, in einsum return c_einsum(*operands, **kwargs) ValueError: operands could not be broadcast together with remapped shapes [original->remapped]: (500,8,1,500)->(500,8,500,newaxis,1) (1,64,64)->(64,64,1)

[huanqingxu]

1000, 1000, 3) (256, 256, 1) torch.Size([500, 8, 1, 500]) torch.Size([1, 64, 64]) torch.Size([500, 8, 1, 500]) Traceback (most recent call last): File "/media/lab549/Data/Medical-Transformer-main/train.py", line 140, in output = model(X_batch) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 152, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 162, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 85, in parallel_apply output.reraise() File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/_utils.py", line 394, in reraise raise self.exc_type(msg) RuntimeError: Caught RuntimeError in replica 0 on device 0. Original Traceback (most recent call last): File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker output = module(*input, **kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 717, in forward return self._forward_impl(x) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 642, in _forward_impl x1 = self.layer1(x) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/container.py", line 100, in forward input = module(input) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 337, in forward out = self.hight_block(out) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 161, in forward qr = torch.einsum('bgci,cij->bgij', q, q_embedding) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/functional.py", line 241, in einsum return torch._C._VariableFunctions.einsum(equation, operands) RuntimeError: size of dimension does not match previous size, operand 1, dim 1

[Agigina]

兄弟们，你们的解决了吗，我也是一样的问题

[jeya-maria-jose]

Yes, with the current code setup, this network needs fixed image size for all images in dataset as input.

[123xu223]

File "train.py", line 140, in output = model(X_batch) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 507, in forward return self._forward_impl(x) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 485, in _forward_impl x1 = self.layer1(x) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\container.py", line 139, in forward input = module(input) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 331, in forward out = self.hight_block(out) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 157, in forward qr = torch.einsum('bgci,cij->bgij', q, q_embedding) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\functional.py", line 299, in einsum return _VF.einsum(equation, operands) # type: ignore[attr-defined] RuntimeError: einsum(): operands do not broadcast with remapped shapes [original->remapped]: [2560, 8, 1, 360]->[2560, 8, 360, 1, 1] [1, 64, 64]->[1, 1, 64, 64, 1]

请问你们解决了吗？

[123xu223]

Yes, with the current code setup, this network needs fixed image size for all images in dataset as input.

I came across a new error report,　You said before that the size of the input image is different, but my image size is the same this time, but I still report this error.　

Total_params: 1347266 Traceback (most recent call last): File "train.py", line 140, in output = model(X_batch) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 507, in forward return self._forward_impl(x) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 485, in _forward_impl x1 = self.layer1(x) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\container.py", line 139, in forward input = module(input) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 331, in forward out = self.hight_block(out) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "E:\Medical-Transformer-main\lib\models\axialnet.py", line 157, in forward qr = torch.einsum('bgci,cij->bgij', q, q_embedding) File "D:\anaconda1\envs\Medical-transformer\lib\site-packages\torch\functional.py", line 299, in einsum return _VF.einsum(equation, operands) # type: ignore[attr-defined] RuntimeError: einsum(): operands do not broadcast with remapped shapes [original->remapped]: [2560, 8, 1, 360]->[2560, 8, 360, 1, 1] [1, 180, 180]->[1, 1, 180, 180, 1]

[123xu223]

Yes, with the current code setup, this network needs fixed image size for all images in dataset as input.

I came across a new error report,　You said before that the size of the input image is different, but my image size is the same this time, but I still report this error.　　ｍｙ　ｐｉｃｔｕｒｅ　ｉｓ　１２８０＊７２０　pixel

[wikiy223]

需要设置命令行参数--img_size，要和图片大小一样

[wikiy223]

model = lib.models.axialnet.MedT(img_size = imgsize, imgchan = imgchant)

[wikiy223]

1000, 1000, 3) (256, 256, 1) torch.Size([500, 8, 1, 500]) torch.Size([1, 64, 64]) torch.Size([500, 8, 1, 500]) Traceback (most recent call last): File "/media/lab549/Data/Medical-Transformer-main/train.py", line 140, in output = model(X_batch) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 152, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 162, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 85, in parallel_apply output.reraise() File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/_utils.py", line 394, in reraise raise self.exc_type(msg) RuntimeError: Caught RuntimeError in replica 0 on device 0. Original Traceback (most recent call last): File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker output = module(*input, **kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 717, in forward return self._forward_impl(x) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 642, in _forward_impl x1 = self.layer1(x) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/container.py", line 100, in forward input = module(input) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 337, in forward out = self.hight_block(out) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) File "/media/lab549/Data/Medical-Transformer-main/lib/models/axialnet.py", line 161, in forward qr = torch.einsum('bgci,cij->bgij', q, q_embedding) File "/home/lab549/anaconda3/envs/medt/lib/python3.6/site-packages/torch/functional.py", line 241, in einsum return torch._C._VariableFunctions.einsum(equation, operands) RuntimeError: size of dimension does not match previous size, operand 1, dim 1

我也是这个错误，爱因斯坦求和函数错误

[1999zjq]

回溯（最后一次调用）： 文件“train.py”，第 140 行，在 输出 = 模型（X_batch） 文件“/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules /module.py”，第 1051 行，在 _call_impl 返回 forward_call(*input, **kwargs) 文件“/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axisnet.py”，第 507 行，向前 返回 self._forward_impl(x) 文件 "/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axisnet.py"，第 485 行，在 _forward_impl x1 = self.layer1(x) 文件 "/home/zzp /.local/lib/python3.8/site-packages/torch/nn/modules/module.py”，第 1051 行，在 _call_impl 中 返回 forward_call(*input, **kwargs) 文件“/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules/container.py”，第 139 行，前向 输入 = 模块（输入） 文件“/home/zzp/. local/lib/python3.8/site-packages/torch/nn/modules/module.py”，第 1051 行，在 _call_impl 返回 forward_call(*input, **kwargs) 文件“/home/zzp/2t/binzhang/Medical -Transformer/lib/models/axisnet.py”，第 331 行，in forward out = self.hight_block(out) File “/home/zzp/.local/lib/python3.8/site-packages/torch/nn/modules /module.py”，第 1051 行，在 _call_impl 中 返回 forward_call(*input, **kwargs) 文件“/home/zzp/2t/binzhang/Medical-Transformer/lib/models/axisnet.py”，第 157 行，向前 qr = torch.einsum('bgci,cij->bgij', q, q_embedding) 文件“/home/zzp/.local/lib/python3.8/site-packages/torch/functional.py”，第 299 行，在 einsum return _VF.einsum(equation, operands) # type: ignore[attr-defined] RuntimeError: einsum(): 操作数不使用重新映射的形状进行广播 [original->remapped]: [2000, 8, 1, 500]->[2000, 8, 500, 1, 1] [1, 64, 64]- >[1, 1, 64, 64, 1]

这个谁解决了吗 我也出现这个问题了

[hczyni]

谢谢，已经解决