Sieun Park (박시은)
Sieun Park (박시은)
Thank you for a great implementation, what do you think is the most appropriate way to use this library inside `pytorch-lightning`?
The paper "[Occlusion-Aware Networks for 3D Human Pose Estimation in Video](https://openaccess.thecvf.com/content_ICCV_2019/papers/Cheng_Occlusion-Aware_Networks_for_3D_Human_Pose_Estimation_in_Video_ICCV_2019_paper.pdf)"[1] published in ICCV 2019 achieves 42.9 MPJPE(protocol 1) and 32.8 P-MPJPE(protocol 2) while your paper[2] achieves 43.0 MPJPE and...
### Description There appears to be a typo in the `_strip_string` function of the `math_equivalence.py` file, where an unnecessary escape character is used with the percent sign. The code uses...
As link feature of config is already implemented, I should deprecate `const_cfg`.
- KL-loss based KD - self-distillation - distillation-based loss functions - - Early stopping KD - On the Efficacy of Knowledge Distillation - FitNets - A Comprehensive Overhaul of Feature...
- Add config for computing metrics(mAP, AR) - Internally implement `mmdetection` transforms - Add config for other representative experiments: - Timm: [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/timm_example/retinanet_timm_efficientnet_b1_fpn_1x_coco.py) - Faster R-CNN(using COCO dataset) [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) - Cascade-mask...
According to [docs](https://pytorch-lightning.readthedocs.io/en/stable/extensions/datamodules.html), `pl.LightningDataModule` can modularize and better organize data-related code.
`visualize.py` to perform inference from image or folder path and save the result to file. - [ ] Image classification - [ ] Object detection
- [ ] Semantic segmentation - [ ] Instance segmentation - [ ] Panoptic segmentation - [ ] Pose estimation - [ ] 2d->3d pose lifting - [ ] 3d...