Couldn't find any class folder in /content/drive/MyDrive/Person_reID_baseline_pytorch/Market-1501-v15.09.15/pytorch/query

[MetehanYasar11]

After I train the model with tutorial dataset, I tried to run this command below in colab;

!python test.py --gpu_ids 0 --name ft_ResNet50 --batchsize 32 --which_epoch 59 --test_dir /content/drive/MyDrive/Person_reID_baseline_pytorch/Market-1501-v15.09.15/pytorch

and I get this error;

This is not an error. If you want to use low precision, i.e., fp16, please install the apex with cuda support (https://github.com/NVIDIA/apex) and update pytorch to 1.0
We use the scale: 1
Traceback (most recent call last):
File "/content/drive/MyDrive/Person_reID_baseline_pytorch/test.py", line 146, in
image_datasets = {x: datasets.ImageFolder( os.path.join(data_dir,x) ,data_transforms) for x in ['gallery','query']}
File "/content/drive/MyDrive/Person_reID_baseline_pytorch/test.py", line 146, in
image_datasets = {x: datasets.ImageFolder( os.path.join(data_dir,x) ,data_transforms) for x in ['gallery','query']}
File "/usr/local/lib/python3.10/dist-packages/torchvision/datasets/folder.py", line 309, in init
super().init(
File "/usr/local/lib/python3.10/dist-packages/torchvision/datasets/folder.py", line 144, in init
classes, class_to_idx = self.find_classes(self.root)
File "/usr/local/lib/python3.10/dist-packages/torchvision/datasets/folder.py", line 218, in find_classes
return find_classes(directory)
File "/usr/local/lib/python3.10/dist-packages/torchvision/datasets/folder.py", line 42, in find_classes
raise FileNotFoundError(f"Couldn't find any class folder in {directory}.")
FileNotFoundError: Couldn't find any class folder in /content/drive/MyDrive/Person_reID_baseline_pytorch/Market-1501-v15.09.15/pytorch/query.

When I look into /content/drive/MyDrive/Person_reID_baseline_pytorch/Market-1501-v15.09.15/pytorch/query, there is nothing...

[layumi]

Hi @MetehanYasar11
Do you download the dataset? and successfully use prepare.py to make sub-folders?

[MetehanYasar11]

Hi @MetehanYasar11 Do you download the dataset? and successfully use prepare.py to make sub-folders?

Yes, I have downloaded dataset and and executed succesfully prepare.py and train.py

[layumi]

Hi @MetehanYasar11
Ok. Is it good with Person_reID_baseline_pytorch/Market-1501-v15.09.15/pytorch/train and gallery?