tf-cpn

tf-cpn copied to clipboard

> @dagongji10 Excuse me, can I ask you a question? Must I provide bbox of pictures when I test a picture?Could you please give me a script which can visualize test results like what you show? Thank you very much

3

> @dagongji10 Excuse me, can I ask you a question? Must I provide bbox of pictures when I test a picture?Could you please give me a script which can visualize...

huigoing

单张图像测试程序

1

哈喽，你们会考虑编写单张图像或视频流的测试程序吗？

Qidian213

As the title said, is it possible to add new joint in the skel and retrain the model with this new skel ?

benMOOVENCY

How to decrease Batch size

4

Hi, how we can decrease batch size for small GPU? I tried in mpest and confiq.py file but I got error "List out of index".

lisa676

About detect single person

16

I use FPN to detect person，when there are many people and close to each other, the box will get some overlap. Just as below picture show.  Is there any...

dagongji10

Hello! I want to speed up the testing process, so I'm thinking to use just GlobalNet, without RefineNet. Do you think this could work without losing too much AP? Also...

biras11

just global net with OHKM

1

I read the code, and it seems that the result is just inferred from refine net. Refine net with OHKM gets better results. It seems refine net gets better features...

lxgen

More training detatils

1

How many epochs did you use to train the models? Did you train the different models using different epochs？ I read your paper. You said, the learning rate is decreased...

Youngkl0726

Train Details

2

First of all, thanks for sharing the work. You used 8 Titank GPUs for training . Now, I want to retrain the keypoints detection model as you using COCO dataset...

ZhongXiaoFang

Batch size

3

How do you think a batch size of 8 versus the batch size you used affect the final output? Have you experimented with batch size at all to see the...

ttdd11