类型错误： __init__() 为参数'dim'获取了多个值

Question

我正在对两个训练过的模型进行测试。首先，我在测试期间得到以下错误，因此我已将torch.logsoftmax类更改为nn.LogSoftmax。

from torch.utils.data import Dataset, DataLoader
import pandas as pd
from torchvision import transforms
from PIL import Image
import torch
import torch.nn as nn
from glob import glob
from pathlib import PurePath
import numpy as np
import timm
import torchvision
import time
img_list = glob('/media/cvpr/CM_22/OOD-CV-phase2/phase2-cls/images/*.jpg')
name_list = [
'aeroplane',
'bicycle',
'boat',
'bus',
'car',
'chair',
'diningtable',
'motorbike',
'sofa',
'train'
]
# conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 cudatoolkit=10.2 -c pytorch
class PoseData(Dataset):
def __init__(self, transforms) -> None:
"""
the data folder should look like
- datafolder
- Images
- labels.csv        
"""
super().__init__()
self.img_list = glob('/media/cvpr/CM_22/OOD-CV-phase2/phase2-cls/images/*.jpg')
self.img_list = sorted(self.img_list, key=lambda x: eval(PurePath(x).parts[-1][:-4]))
self.trs = transforms
def __len__(self):
return len(self.img_list)
def __getitem__(self, index):
image_dir = self.img_list[index]
image_name = PurePath(image_dir).parts[-1]
image = Image.open(image_dir)
image = self.trs(image)
return image, image_name

if __name__ == "__main__":
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
tfs = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
normalize,
])
model1 = timm.models.swin_base_patch4_window7_224(pretrained=False, num_classes=15)
model1 = torch.nn.DataParallel(model1)
model1.load_state_dict(torch.load('/media/cvpr/CM_22/OOD_CV/swin15_best.pth.tar')['state_dict'],strict=False)
model1 = model1.cuda()
model1.eval()
model2 = timm.models.convnext_base(pretrained=False, num_classes=15)
model2 = torch.nn.DataParallel(model2)
model2.load_state_dict(torch.load('convnext15_best.pth.tar')['state_dict'],strict=False)
model2 = model2.cuda()
model2.eval()
dataset = PoseData(tfs)
loader = DataLoader(dataset, batch_size=128, shuffle=False, drop_last=False, num_workers=4)
image_dir = []
preds = []
for image, pth in loader:
image_dir.append(list(pth))
image = image.cuda()
with torch.no_grad():
model1.eval()
pred1 = model1(image)
model2.eval()
pred2 = model2(image)
entropy1 = -torch.sum(torch.softmax(pred1[:, :10], dim=1) * nn.LogSoftmax(pred1[:, :10], dim=1), dim=-1,
keep_dim=True)
entropy2 = -torch.sum(torch.softmax(pred2[:, :10], dim=1) * nn.LogSoftmax(pred2[:, :10], dim=1), dim=-1,
keep_dim=True)
entropy = entropy1 + entropy2
pred = torch.softmax(pred1[:, :10], dim=1) * (entropy - entropy1) / entropy + torch.softmax(pred2[:, :10],
                                  dim=1) * (
entropy - entropy2) / entropy
pred = torch.argmax(pred[:, :10], dim=1)
p = []
for i in range(pred.size(0)):
p.append(name_list[pred[i].item()])
p = np.array(p)
preds.append(p)
print(len(np.concatenate(preds)))
image_dir = np.array(sum(image_dir, []))
preds = np.concatenate(preds)
csv = {'imgs': np.array(image_dir), 'pred': np.array(preds),
}
csv = pd.DataFrame(csv)
print(csv)
csv.to_csv('results.csv', index=False)

回溯

return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Traceback (most recent call last):
File "/media/cvpr/CM_22/OOD_CV/test.py", line 93, in <module>
entropy1 = -torch.sum(torch.softmax(pred1[:, :10], dim=1) * torch.logsoftmax(pred1[:, :10], dim=1), dim=-1,
AttributeError: module 'torch' has no attribute 'logsoftmax'

由于PyTorch版本冲突，我已经替换为最近的PyTorch版本，但现在得到dim错误

return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Traceback (most recent call last):
File "/media/cvpr/CM_22/OOD_CV/test.py", line 93, in <module>
entropy1 = -torch.sum(torch.softmax(pred1[:, :10], dim=1) * nn.LogSoftmax(pred1[:, :10], dim=1), dim=-1,
TypeError: __init__() got multiple values for argument 'dim'

实施后

nn.LogSoftMax(dim=1)(pred1[:, :10])

回溯

entropy1 = -torch.sum(torch.softmax(pred1[:, :10], dim=1) * nn.LogSoftmax(dim=1)(pred1[:, :10]), dim=-1, keep_dim=True)
TypeError: sum() received an invalid combination of arguments - got (Tensor, keep_dim=bool, dim=int), but expected one of:
* (Tensor input, *, torch.dtype dtype)
didn't match because some of the keywords were incorrect: keep_dim, dim
* (Tensor input, tuple of ints dim, bool keepdim, *, torch.dtype dtype, Tensor out)
* (Tensor input, tuple of names dim, bool keepdim, *, torch.dtype dtype, Tensor out)

删除keep_dim=True参数

回溯

Traceback (most recent call last):
File "/media/cvpr/CM_22/OOD_CV/test.py", line 97, in <module>
pred = torch.softmax(pred1[:, :10], dim=1) * (entropy - entropy1) / entropy + torch.softmax(pred2[:, :10],
RuntimeError: The size of tensor a (10) must match the size of tensor b (128) at non-singleton dimension 1

Answer 1

LogSoftMax是一个模块，必须首先实例化，然后调用(这是当它的forward方法被执行)。试试这个:

entropy1 = -torch.sum(torch.softmax(pred1[:, :10], dim=1) * nn.LogSoftmax(dim=1)(pred1[:, :10]), dim=-1, keepdim=True)

相反，你也可以使用这个模块的函数形式:

torch.nn.functional.log_softmax(pred1[:, :10], dim=1)