model = model_.ResNet_pca(nclasses=args.n_classes)
elif args.model == 'lcnn_9':
model = model_.lcnn_9layers(nclasses=args.n_classes)
elif args.model == 'lcnn_29':
model = model_.lcnn_29layers_v2(nclasses=args.n_classes)
elif args.model == 'lcnn_9_pca':
model = model_.lcnn_9layers_pca(nclasses=args.n_classes)
elif args.model == 'lcnn_29_pca':
model = model_.lcnn_29layers_v2_pca(nclasses=args.n_classes)
elif args.model == 'lcnn_9_icqspec':
model = model_.lcnn_9layers_icqspec(nclasses=args.n_classes)
elif args.model == 'lcnn_9_prodspec':
model = model_.lcnn_9layers_prodspec(nclasses=args.n_classes)
elif args.model == 'lcnn_9_CC':
model = model_.lcnn_9layers_CC(nclasses=args.n_classes,
ncoef=args.ncoef,
init_coef=args.init_coef)
elif args.model == 'lcnn_29_CC':
model = model_.lcnn_29layers_CC(nclasses=args.n_classes,
ncoef=args.ncoef,
init_coef=args.init_coef)
elif args.model == 'resnet_CC':
model = model_.ResNet_CC(nclasses=args.n_classes,
ncoef=args.ncoef,
init_coef=args.init_coef)
if args.pretrained_path is not None:
ckpt = torch.load(args.pretrained_path,
map_location=lambda storage, loc: storage)
try:
elif args.model == 'resnet_pca':
model = model_.ResNet_pca()
elif args.model == 'lcnn_9':
model = model_.lcnn_9layers()
elif args.model == 'lcnn_29':
model = model_.lcnn_29layers_v2()
elif args.model == 'lcnn_9_pca':
model = model_.lcnn_9layers_pca()
elif args.model == 'lcnn_29_pca':
model = model_.lcnn_29layers_v2_pca()
elif args.model == 'lcnn_9_icqspec':
model = model_.lcnn_9layers_icqspec()
elif args.model == 'lcnn_9_prodspec':
model = model_.lcnn_9layers_prodspec()
elif args.model == 'lcnn_9_CC':
model = model_.lcnn_9layers_CC(ncoef=args.ncoef,
init_coef=args.init_coef)
elif args.model == 'lcnn_29_CC':
model = model_.lcnn_29layers_CC(ncoef=args.ncoef,
init_coef=args.init_coef)
elif args.model == 'resnet_34_CC':
model = model_.ResNet_34_CC(ncoef=args.ncoef, init_coef=args.init_coef)
print('Loading model')
ckpt = torch.load(args.cp_path, map_location=lambda storage, loc: storage)
model.load_state_dict(ckpt['model_state'], strict=True)
model.eval()
print('Model loaded')
print('Loading data')
elif args.model_la == 'resnet_pca':
model_la = model_.ResNet_pca()
elif args.model_la == 'lcnn_9':
model_la = model_.lcnn_9layers()
elif args.model_la == 'lcnn_29':
model_la = model_.lcnn_29layers_v2()
elif args.model_la == 'lcnn_9_pca':
model_la = model_.lcnn_9layers_pca()
elif args.model_la == 'lcnn_29_pca':
model_la = model_.lcnn_29layers_v2_pca()
elif args.model_la == 'lcnn_9_icqspec':
model_la = model_.lcnn_9layers_icqspec()
elif args.model_la == 'lcnn_9_prodspec':
model_la = model_.lcnn_9layers_prodspec()
elif args.model_la == 'lcnn_9_CC':
model_la = model_.lcnn_9layers_CC(ncoef=args.ncoef_la)
elif args.model_la == 'lcnn_29_CC':
model_la = model_.lcnn_29layers_CC(ncoef=args.ncoef_la)
elif args.model_la == 'resnet_CC':
model_la = model_.ResNet_CC(ncoef=args.ncoef_la)
if args.model_pa == 'lstm':
model_pa = model_.cnn_lstm()
elif args.model_pa == 'resnet':
model_pa = model_.ResNet()
elif args.model_pa == 'resnet_pca':
model_pa = model_.ResNet_pca()
elif args.model_pa == 'lcnn_9':
model_pa = model_.lcnn_9layers()
elif args.model_pa == 'lcnn_29':
model_pa = model_.lcnn_29layers_v2()
if args.model == 'lcnn_29_pca' or args.model == 'all':
batch = torch.rand(3, 1, 120, 300)
model = model_.lcnn_29layers_v2_pca()
mu = model.forward(batch)
print('lcnn_29_pca', mu.size())
if args.model == 'lcnn_9_icqspec' or args.model == 'all':
batch = torch.rand(3, 1, 256, 300)
model = model_.lcnn_9layers_icqspec()
mu = model.forward(batch)
print('lcnn_9_icqspec', mu.size())
if args.model == 'lcnn_9_prodspec' or args.model == 'all':
batch = torch.rand(3, 1, 257, 300)
model = model_.lcnn_9layers_prodspec()
mu = model.forward(batch)
print('lcnn_9_prodspec', mu.size())
if args.model == 'lcnn_9_CC' or args.model == 'all':
batch = torch.rand(3, 1, 90, 300)
model = model_.lcnn_9layers_CC()
mu = model.forward(batch)
print('lcnn_9_CC', mu.size())
if args.model == 'lcnn_29_CC' or args.model == 'all':
batch = torch.rand(3, 1, 90, 300)
model = model_.lcnn_29layers_CC()
mu = model.forward(batch)
print('lcnn_29_CC', mu.size())
if args.model == 'resnet_34_CC' or args.model == 'all':
batch = torch.rand(3, 1, 90, 300)
model = model_.ResNet_34_CC()
mu = model.forward(batch)
print('resnet_34_CC', mu.size())