Open ssbilakeri opened 4 years ago
@ssbilakeri
Sorry for the late response. Did you run your code on Windows?
Pytorch supports for multi-processing on Windows is not good. So you may try to set nworkers=0
in dataloader.
Hello You have done excellent and impressive work. Actually, I am new in machine learning and I was trying to run the code but I was facing problems. It would be grateful if you help me
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 [Resize(size=(256, 128), interpolation=PIL.Image.BICUBIC), Pad(padding=10, fill=0, padding_mode=constant), RandomCrop(size=(256, 128), padding=None), RandomHorizontalFlip(p=0.5), ToTensor(), Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])]
Traceback (most recent call last):
File "
what would have to put in 'model' folder?
Hi @atul2oct
Sorry...I just see your reply.
No. Actally, from model import ft_net, ft_net_dense, ft_net_NAS, PCB
is to load the function from model.py
.
There is no relation with the folder model
.
After running train.py file I'm getting This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module:
How to fix it