parser = argparse.ArgumentParser()
parser.add_argument('--sparsity',
type=float,
default=0.5,
help='Sparsity ratio')
parser.add_argument('--save_dir',
type=str,
default='./',
help='Where to save retrained model')
args, _ = parser.parse_known_args()
device = 'cuda'
if __name__ == '__main__':
sparse_model_path = os.path.join(args.save_dir, 'mynet_sparse.pth')
assert os.path.exists(sparse_model_path), "No sparse model!"
slim_model_path = os.path.join(args.save_dir, 'mynet_slim.pth')
sparse_model = MyNet()
sparse_model = load_weights(sparse_model, sparse_model_path)
sparse_model.to(device)
input_signature = torch.randn([1, 3, 32, 32], dtype=torch.float32)
input_signature = input_signature.to(device)
pruning_runner = get_pruning_runner(sparse_model, input_signature,
'iterative')
slim_model = pruning_runner.prune(removal_ratio=args.sparsity, mode='slim')
torch.save(slim_model.state_dict(), slim_model_path)
print('Convert sparse model to slim model done!')
num_workers=args.num_workers,
shuffle=True,
train=True,
download=download)
val_loader = get_dataloader_ddp(args.data_dir,
batch_size,
num_workers=args.num_workers,
shuffle=False,
train=False,
download=download)
model = MyNet()
model = load_weights(model, args.pretrained)
input_signature = torch.randn([1, 3, 32, 32], dtype=torch.float32)
input_signature = input_signature.to(device)
model = model.to(device)
pruning_runner = get_pruning_runner(model, input_signature, 'iterative')
model = pruning_runner.prune(removal_ratio=args.sparsity, mode='sparse')
model = torch.nn.parallel.DistributedDataParallel(
model,
device_ids=[args.local_rank],
output_device=args.local_rank,
find_unused_parameters=True)
criterion = torch.nn.CrossEntropyLoss().cuda()
optimizer = torch.optim.Adam(model.parameters(),
args.lr,
weight_decay=args.weight_decay)
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer, args.epochs)
best_acc1 = 0
args, _ = parser.parse_known_args()
device = 'cuda'
gpus = get_gpus(args.gpus)
if __name__ == '__main__':
model = MyNet()
model = torch.nn.DataParallel(model, device_ids=gpus)
batch_size = args.batch_size * len(gpus)
if os.path.exists(args.data_dir):
download = False
else:
download = True
val_loader = get_dataloader(args.data_dir,
batch_size,
num_workers=args.num_workers,
shuffle=False,
train=False,
download=download)
model.to(device)
criterion = torch.nn.CrossEntropyLoss().cuda()
if not os.path.exists(args.pretrained):
print('Pretrained model do not exist!')
model.load_state_dict(torch.load(args.pretrained))
acc1, acc5 = evaluate(val_loader, model, criterion)
print('acc1={},acc5={}'.format(acc1, acc5))
