num_classes=num_classes,
train=False,
transform=transform)
logger.info("Dataset samples: {}".format(len(train_set) + len(val_set)))
train_loader = DataLoader(train_set,
batch_size=batch_size,
shuffle=True,
num_workers=24,
pin_memory=True)
val_loader = DataLoader(val_set,
batch_size=batch_size,
shuffle=False,
num_workers=24,
pin_memory=True)
# Create model
model = r2plus1d_18(pretrained=True, num_classes=226)
# load pretrained
checkpoint = torch.load('final_models/val_rgb_final.pth')
new_state_dict = OrderedDict()
for k, v in checkpoint.items():
name = k[7:] # remove 'module.'
new_state_dict[name] = v
model.load_state_dict(new_state_dict)
# if phase == 'Train':
# model.fc1 = nn.Linear(model.fc1.in_features, num_classes)
print(model)
model = model.to(device)
# Run the model parallelly
if torch.cuda.device_count() > 1:
sample_duration=sample_duration,
num_classes=num_classes).to(device)
elif args.model == '3dresnet34':
model = resnet34(pretrained=True,
progress=True,
sample_size=sample_size,
sample_duration=sample_duration,
num_classes=num_classes).to(device)
elif args.model == '3dresnet50':
model = resnet50(pretrained=True,
progress=True,
sample_size=sample_size,
sample_duration=sample_duration,
num_classes=num_classes).to(device)
elif args.model == 'r2plus1d':
model = r2plus1d_18(pretrained=True,
num_classes=num_classes).to(device)
# Run the model parallelly
if torch.cuda.device_count() > 1:
model = nn.DataParallel(model)
# Load model
model.load_state_dict(torch.load(model_path))
# Test the model
model.eval()
all_label = []
all_pred = []
with torch.no_grad():
for batch_idx, data in enumerate(test_loader):
# get the inputs and labels
inputs, labels = data['data'].to(device), data['label'].to(device)
num_classes=num_classes,
train=False,
transform=transform)
logger.info("Dataset samples: {}".format(len(train_set) + len(val_set)))
train_loader = DataLoader(train_set,
batch_size=batch_size,
shuffle=True,
num_workers=num_workers,
pin_memory=True)
val_loader = DataLoader(val_set,
batch_size=batch_size,
shuffle=False,
num_workers=num_workers,
pin_memory=True)
# Create model
model = r2plus1d_18(pretrained=False, num_classes=226)
# load pretrained
checkpoint = torch.load('final_models_finetuned/hha_final_finetuned.pth')
new_state_dict = OrderedDict()
for k, v in checkpoint.items():
name = k[7:] # remove 'module.'
new_state_dict[name] = v
model.load_state_dict(new_state_dict)
# if phase == 'Train':
# model.fc1 = nn.Linear(model.fc1.in_features, num_classes)
print(model)
model = model.to(device)
# Run the model parallelly
if torch.cuda.device_count() > 1:
logger.info("Using {} GPUs".format(torch.cuda.device_count()))
mode='val',
transform=val_transform)
training_dataloader = DataLoader(train_data,
batch_size=batch_size,
shuffle=True,
num_workers=16,
pin_memory=True)
validation_dataloader = DataLoader(val_data,
batch_size=batch_size,
shuffle=True,
num_workers=16,
pin_memory=True)
if args.model == 'r2plus1d_18':
model = cnn3d = r2plus1d_18(pretrained=False, num_classes=500)
elif args.model == 'r2plus1d_18_new':
model = r2plus1d_18_new(pretrained=False, progress=False)
elif args.model == '3dresnet18':
model = resnet18(pretrained=False,
sample_size=sample_size,
sample_duration=16,
num_classes=500)
elif args.model == 'ResCRNN':
model = ResCRNN(sample_size=112,
sample_duration=16,
num_classes=100,
arch="resnet18")
model = nn.DataParallel(model, device_ids=[0, 1, 2, 3], dim=0).to(device)
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=lr, weight_decay=0.0001)