Open claudehang opened 5 years ago
Hi, the slim resnet50 checkpoint can be downloaded from the official page. As for the tfrecords, they are cumbersome, expecially for NTU. We can work out some way to share them, otherwise @ncgarcia may share the code to create them from the original videos.
Thanks~ I am a PyTorch user and new to TensorFlow, so really appreciate your code and later release of data part!
Could you just provide the .tfrecord
files for train/val/test data? That way the training process can get started. Thanks a lot!
Hi claudehang, I'm sorry for the late reply. I'm committing the code used to produce the tfrecords (commit c7a411a53a9fcda9a021a743d7f0e213ac845a37) It is only needed to download the dataset (uwa3D) and adjust the paths to the RGB and Depth frames folders. The process is the same for the other datasets, excluding the small adjusts for the filenames and labels. thanks!
imagenet_ckpt = '/home/pavis/Documents/ng/tf-ckpt/resnet_v1_50.ckpt' uwa3dii_dir = '/media/pavis/3TB-HD2/datasets/uwa3dii/tfrecords/' ntu_dir = '/datasets/ntu/tfrecords_aligned_improved/' nwucla_dir = '/datasets/nwucla/tfrecords/'
Could you share the related data in these folders? Many thanks!