Age | Commit message (Collapse) | Author | |
---|---|---|---|
2021-01-11 | Implement evaluator | Jordan Gong | |
2021-01-09 | Fix NaN when separate sum is zero | Jordan Gong | |
2021-01-07 | Add typical training script and some bug fixes | Jordan Gong | |
1. Resolve deprecated scheduler stepping issue 2. Make losses in the same scale(replace mean with sum in separate triplet loss, enlarge pose similarity loss 10x) 3. Add ReLU when compute distance in triplet loss 4. Remove classes except Model from `models` package init | |||
2021-01-07 | Change device config and add enable multi-GPU computing | Jordan Gong | |
1. Add `disable_acc` switch for disabling accelerator. When it is off, system will automatically choosing accelerator. 2. Enable multi-GPU training using torch.nn.DataParallel | |||
2021-01-05 | Implement Batch All Triplet Loss | Jordan Gong | |
2021-01-03 | Update hyperparameter configuration, implement prototype fit function | Jordan Gong | |
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 | |