1st place solution (Team StylingAI Inc. & PKU AIIC) for CVPR 2020 DeepFashion2 Clothes Landmark Detection Track. Aggregation and Finetuning for Clothes Landmark Detection
First of all, congrats for 1st place in DeepFashion2 competition! 1st_place_medal
I want to test your model for my term project. Is there any pretrained weights you can share. If so, I would be so happy.
Thank you.
Hi! I notice that when you do fine-tuning for every category with the det_bbox_result, you set det_file = f'../htcdet/htc-{test_or_validation_set}-det-result-3scale-hflip.bbox.json_'f'{category_id}.json'. How do you get the detection result for every category? Is that separated from the whole result got in detection stage or you did detection for every category? Looking forward for reply. Thanks!!!
Traceback (most recent call last):
File "tools/train.py", line 248, in
main()
File "tools/train.py", line 137, in main
normalize,
File "E:\DeepFashion2_Dataset\HRNet-Human-Pose-Estimation\tools..\lib\dataset\deepfashion2.py", line 172, in init
self.db = self._get_db()
File "E:\DeepFashion2_Dataset\HRNet-Human-Pose-Estimation\tools..\lib\dataset\deepfashion2.py", line 197, in _get_db
gt_db = self._load_coco_person_detection_results()
File "E:\DeepFashion2_Dataset\HRNet-Human-Pose-Estimation\tools..\lib\dataset\deepfashion2.py", line 319, in _load_coco_person_detection_results
det_res = all_boxes[n_img]
KeyError: 0
Hello, how do I get the annotations_agG81kps, annotations_per_category, and annotations_per_category_AGG81kps files in the Data/Deepfashion2 / directory
First of all, congrats for 1st place in DeepFashion2 competition! ๐ฅ
It is very impressive for me and I'm trying to follow up your method for finding keypoints in the dataset.
Is there any .json file with aggregated keypoints or a method for making aggregated keypoint label file?