Roman

resize images to 256, because originally the video in 224x224 is loaded. For example, in frames_dataset.py: ``` video_array = video_array[frame_idx] video_array = [resize(frame, self.frame_shape[:2])[..., :3] for frame in video_array] ```

Can I train Instance Segmentation without a Semantic Segmentation branch in HTC?

Hi, Here are the raw results for our models: https://drive.google.com/drive/folders/1fdXgVV_6L5iQ5xcQAudYyU5WZVfsoyUm?usp=share_link For evaluation, we use the Got10K toolkit: https://github.com/got-10k/toolkit