Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

vision classification QAT tutorial: fix for DDP (redo) #2230

Merged
merged 1 commit into from
May 18, 2020
Merged

vision classification QAT tutorial: fix for DDP (redo) #2230

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions references/classification/train_quantization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,6 @@ def main(args):
print("Creating model", args.model)
# when training quantized models, we always start from a pre-trained fp32 reference model
model = torchvision.models.quantization.__dict__[args.model](pretrained=True, quantize=args.test_only)
model.to(device)

if not (args.test_only or args.post_training_quantize):
model.fuse_model()
Expand All @@ -66,6 +65,8 @@ def main(args):
step_size=args.lr_step_size,
gamma=args.lr_gamma)

model.to(device)

criterion = nn.CrossEntropyLoss()
model_without_ddp = model
if args.distributed:
Expand Down Expand Up @@ -129,7 +130,7 @@ def main(args):
print('Evaluate QAT model')

evaluate(model, criterion, data_loader_test, device=device)
quantized_eval_model = copy.deepcopy(model)
quantized_eval_model = copy.deepcopy(model_without_ddp)
quantized_eval_model.eval()
quantized_eval_model.to(torch.device('cpu'))
torch.quantization.convert(quantized_eval_model, inplace=True)
Expand Down