MobileFaceNet model generated
Traceback (most recent call last):
File "train.py", line 30, in
learner = face_learner(conf)
File "F:\Suresh\InsightFace_Pytorch\Learner.py", line 29, in init
self.loader, self.class_num = get_train_loader(conf)
File "F:\Suresh\InsightFace_Pytorch\data\data_pipe.py", line 47, in get_train_loader
ds, class_num = get_train_dataset(conf.emore_folder/'imgs')
File "F:\Suresh\InsightFace_Pytorch\data\data_pipe.py", line 24, in get_train_dataset
ds = ImageFolder(imgs_folder,train_transform)
File "C:\Users\cudalab10\Anaconda3\envs\tensorflow\lib\site-packages\torchvision\datasets\folder.py", line 178, in init
target_transform=target_transform)
File "C:\Users\cudalab10\Anaconda3\envs\tensorflow\lib\site-packages\torchvision\datasets\folder.py", line 75, in init
classes, class_to_idx = find_classes(root)
File "C:\Users\cudalab10\Anaconda3\envs\tensorflow\lib\site-packages\torchvision\datasets\folder.py", line 23, in find_classes
classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))]
TypeError: listdir: illegal type for path parameter
ds = ImageFolder(imgs_folder,train_transform) is having 2 parameters
but in torchvision\datasets\folder.py having only 1 parameter.
torchvision version is as per requirements.txt
MobileFaceNet model generated Traceback (most recent call last): File "train.py", line 30, in
learner = face_learner(conf)
File "F:\Suresh\InsightFace_Pytorch\Learner.py", line 29, in init
self.loader, self.class_num = get_train_loader(conf)
File "F:\Suresh\InsightFace_Pytorch\data\data_pipe.py", line 47, in get_train_loader
ds, class_num = get_train_dataset(conf.emore_folder/'imgs')
File "F:\Suresh\InsightFace_Pytorch\data\data_pipe.py", line 24, in get_train_dataset
ds = ImageFolder(imgs_folder,train_transform)
File "C:\Users\cudalab10\Anaconda3\envs\tensorflow\lib\site-packages\torchvision\datasets\folder.py", line 178, in init
target_transform=target_transform)
File "C:\Users\cudalab10\Anaconda3\envs\tensorflow\lib\site-packages\torchvision\datasets\folder.py", line 75, in init
classes, class_to_idx = find_classes(root)
File "C:\Users\cudalab10\Anaconda3\envs\tensorflow\lib\site-packages\torchvision\datasets\folder.py", line 23, in find_classes
classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))]
TypeError: listdir: illegal type for path parameter
ds = ImageFolder(imgs_folder,train_transform) is having 2 parameters but in torchvision\datasets\folder.py having only 1 parameter. torchvision version is as per requirements.txt