Age | Commit message (Collapse) | Author | |
---|---|---|---|
2020-12-31 | Make super class constructor revoke consistent | Jordan Gong | |
2020-12-29 | Add type hint for new label (numpy.int64) | Jordan Gong | |
2020-12-29 | Encode class names to label and some access improvement | Jordan Gong | |
1. Encode class names using LabelEncoder from sklearn 2. Remove unneeded class variables 3. Protect some variables from being accessed in userspace | |||
2020-12-27 | Prepare for FVG dataset | Jordan Gong | |
2020-12-27 | Make naming scheme consistent | Jordan Gong | |
Use `dir` instead of `path` | |||
2020-12-27 | Add dataset selector to config type hint, change ClipLabels typo to ClipViews | Jordan Gong | |
2020-12-27 | Adopt type hinting generics in standard collections (PEP 585) | Jordan Gong | |
2020-12-26 | Sample k more clips for disentanglement | Jordan Gong | |
2020-12-26 | Add config file and corresponding type hint | Jordan Gong | |
2020-12-26 | Combine transformed height and width to `frame_size` | Jordan Gong | |
2020-12-21 | Change image loading technique | Jordan Gong | |
1. Use Pillow.Image.open instead of torchvision.io.read_image to read image 2. Transforming PIL images instead of tensors which performs better and device option is removed 3. Images are normalized now | |||
2020-12-19 | 1. Delete unused transform function | Jordan Gong | |
2. Reorganize the initialization cache dicts | |||
2020-12-19 | Fix indexing error when no clip to be discard | Jordan Gong | |
2020-12-19 | Add cache switch, allowing load all data into RAM before sampling | Jordan Gong | |
2020-12-18 | Implement triplet sampler | Jordan Gong | |
2020-12-18 | Implement CASIA-B dataset | Jordan Gong | |