]
# load data
data_path = '/net/bvisionserver3/playpen10/ammirato/Data/ILSVRC/'
#CREATE TRAIN/TEST splits
data_set = VID_Loader(data_path, 'val_single', target_size=[200, 16])
num_images = 100
batch = True
#test multiple trained nets
for model_name in trained_model_names:
print model_name
# load net
net = TDID()
network.load_net(trained_model_path + model_name + '.h5', net)
print('load model successfully!')
net.cuda()
net.eval()
# evaluation
test_net(model_name,
net,
data_set,
num_images=num_images,
batch=batch,
max_per_target=max_per_target,
thresh=thresh)
meta_fid.write('start from: {}\n'.format(trained_model_name))
meta_fid.close()
#load net definition and init parameters
net = TDID()
if load_trained_model:
#load a previously trained model
if use_batch_norm:
vgg16_bn = models.vgg16_bn(pretrained=False)
net.features = torch.nn.Sequential(*list(vgg16_bn.features.children())[:-1])
net.features.eval()
elif use_torch_vgg:
vgg16 = models.vgg16(pretrained=False)
net.features = torch.nn.Sequential(*list(vgg16.features.children())[:-1])
network.load_net(trained_model_path + trained_model_name, net)
else:
#load pretrained vgg weights, and init everything else randomly
network.weights_normal_init(net, dev=0.01)
if use_batch_norm:
if use_pretrained_vgg:
vgg16_bn = models.vgg16_bn(pretrained=True)
else:
vgg16_bn = models.vgg16_bn(pretrained=False)
net.features = torch.nn.Sequential(*list(vgg16_bn.features.children())[:-1])
net.features.eval()
elif use_torch_vgg:
if use_pretrained_vgg:
vgg16 = models.vgg16(pretrained=True)
else:
vgg16 = models.vgg16(pretrained=False)