Thanh Nguyen

Is it better to handle for the case num = int(line.strip()) = 0?

2

Hi thanks for sharing code. if num = 0 https://github.com/faciallab/FaceDetector/blob/5b588f58884086d005a5ac67bd39a03ce631f8f4/mtcnn/datasets/wider_face.py#L43, for example 10422 0--Parade/0_Parade_Parade_0_452.jpg 10423 0 10424 0 0 0 0 0 0 0 0 0 0 10425 0--Parade/0_Parade_Parade_0_630.jpg then,...

Chaper 4: learning curve

2

Has anyone experienced the ` plot_learning_curves(model, X, y)` ? Why the curve characteristics strongly depends on the `random_state` value , for example 10, 20? The figure below was obtained by...

OpenVINO 2020.1

1

Dear authors, How can I rebuild the image with `OpenVINO 2020.1`?

Applying this technique to detection problem (training on the COCO detection dataset)?

9

Dear @han-cai , Thanks for sharing your excellent work. I am just curious about how we can apply this technique to detection problem (training on the COCO detection dataset)? Appreciate...

bbox annotation format?

3

Dear @ZeroE04 , Thank you for sharing your work. I am not clear about the bbox annotation of your dataset. I guess it is in `xc, yc, w, h, ang`,...

Dear @romeric , Thanks for sharing your work. Let see the following pieces of code: ``` Tensor m1 = {{1,1},{2,2}}; Tensor m2 = {{3,3},{4,4}}; Tensor m3 = inner(m1, m2); ```...

PCK

6

Dose anyone know why divided by 10 here: https://github.com/microsoft/human-pose-estimation.pytorch/blob/18f1d0fa5b5db7fe08de640610f3fdbdbed8fb2f/lib/core/evaluate.py#L55

Hi, thanks for providing the code. Have you tried the invariant rotation property? I already tested, but it does not work well.

Model performance

7

Dear @jahongir7174 , Thanks for sharing your work. I am curious about how your train models performance compared to the pytorch version?

Dear @SupreethN , I would like to know about the license of the COCO-Hand and TV-Hand datasets.