| | |
| | | # ResNet101 with 3 outputs. |
| | | # model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 23, 3], 66) |
| | | # ResNet50 |
| | | model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66) |
| | | model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, 0) |
| | | # ResNet18 |
| | | # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66) |
| | | |
| | |
| | | print 'Loading data.' |
| | | |
| | | transformations = transforms.Compose([transforms.Scale(224), |
| | | transforms.RandomCrop(224), transforms.ToTensor(), |
| | | transforms.CenterCrop(224), transforms.ToTensor(), |
| | | transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])]) |
| | | |
| | | model.cuda(gpu) |
| | |
| | | idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu) |
| | | |
| | | video = cv2.VideoCapture(video_path) |
| | | width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH)) # float |
| | | height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT)) # float |
| | | |
| | | # New cv2 |
| | | # width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH)) # float |
| | | # height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT)) # float |
| | | # |
| | | # # Define the codec and create VideoWriter object |
| | | # fourcc = cv2.VideoWriter_fourcc(*'MJPG') |
| | | # out = cv2.VideoWriter('output/video/output-%s.avi' % args.output_string, fourcc, 30.0, (width, height)) |
| | | |
| | | # Old cv2 |
| | | width = int(video.get(cv2.cv.CV_CAP_PROP_FRAME_WIDTH)) # float |
| | | height = int(video.get(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT)) # float |
| | | |
| | | # Define the codec and create VideoWriter object |
| | | fourcc = cv2.VideoWriter_fourcc(*'MJPG') |
| | | fourcc = cv2.cv.CV_FOURCC(*'MJPG') |
| | | out = cv2.VideoWriter('output/video/output-%s.avi' % args.output_string, fourcc, 30.0, (width, height)) |
| | | |
| | | txt_out = open('output/video/output-%s.txt' % args.output_string, 'w') |
| | |
| | | img_shape = img.size() |
| | | img = img.view(1, img_shape[0], img_shape[1], img_shape[2]) |
| | | img = Variable(img).cuda(gpu) |
| | | yaw, pitch, roll = model(img) |
| | | yaw, pitch, roll, angles = model(img) |
| | | |
| | | yaw_predicted = F.softmax(yaw) |
| | | pitch_predicted = F.softmax(pitch) |