-
Hi,
I am trying to load a set of images that are attached by a set of custom matches. These keypoints and thereby the matches between the images, are evaluated offline by some custom feature extrac…
-
thank you for sharing the code.
After reading the code , I doubt that there is something wrong with [the line](https://github.com/brookicv/imageRetrieval/blob/master/src/siftDetector.cpp#L55) where…
-
In image_dataset.py, if we activate shuffle_mode and then the image will be cropped. Now if a person is cropped out of the region, the 2d kps will mostly fall out of the image region, and these outlie…
-
Dear author,
I encountered an issue when training on coco keypoints dataset. I just adjusted num_layers from 50 to 18, i.e, res18, and started to train based on coco keypoints dataset. The loss wen…
-
**Describe the bug**
-
Can this model be used for human keypoint detection？
-
(mmlab) a@R4-610-AI:/media/a/Data-2/MMAction/mmaction2$ python demo/webcam_demo.py work_dirs_2/slowonly_r50_u48_240e_ntu120_xsub_keypoint/slowonly_r50_u48_240e_ntu120_xsub_keypoint.py work_dirs_2/slow…
-
> TEST:
AUG:
ENABLED: false
FLIP: true
MAX_SIZE: 4000
MIN_SIZES:
- 400
- 500
- 600
- 700
- 800
- 900
- 1000
- 1100
- 1200
DETECTI…
-
as mentined in README file, the yolo family using a unique label formatting, it would be more convenient if a simple script to generate yolo style annotation are provided, which can transfer arbitary…
-
## ❓ Questions and Help
Hi, I found out that when KEYPOINT_HEAD.SHARE_BOX_FEATURE_EXTRACTOR=True, the feature_extractor of keypoint_head becomes identical to the ones of bbox_head, which composed of …