junedgar

Results 11 issues of junedgar

It's a amazing work, but I coundn't understand the codes about MIL. Can you share more detail about this work.

I ran the video_tracking.py with GPU. But it worked so slowly. The log's output is below: ```Frame: 0/72 Time required: 860.9sec 6235 vertices and 1 classes and 6536778 edges starting...

hi , Thank you for your great job. I tried to get the 7354 classes chinese charaters, but i only got 3755 classes from CASIA-HWDB1.0-HWDB1.1 . I couldn't find the...

I did the 'make' step successful. But when i did the 'python setup.py install' with the error blow: ![image](https://cloud.githubusercontent.com/assets/17995658/26812908/41713d2a-4aad-11e7-98b2-088f3849df02.png) environment: mac 10.12.5 tensorflow 1.1.0

Thank you for your great work! Can you share the data augemantation code?

Thank you for your great work! I tried to train the model with shufflenet, but the loss turn to Nan. Can you give me some advices? ``` Epoch: [0][0/1520] Data...

你好,camera.yml中,为什么cam_0_distcoeffs参数是五个,opencv校正后的畸变参数好像是四个

I tried to defish the fisheye image with 130° or 160° fisheye len. But I didn't get the good result like you. org image: ![image](https://user-images.githubusercontent.com/17995658/40764686-99730b76-64dc-11e8-8675-9a5f42a9bca4.png) corrected result: ![image](https://user-images.githubusercontent.com/17995658/40764705-a5933c96-64dc-11e8-8198-e10662e78af8.png) Is there...

Thank you for your great work! Can you share the pre-trained weights for model test?

hi , thank you for your great job. I can't find the trained model where you described in [output directory](https://github.com/DetectionTeamUCAS/SSH_Tensorflow/tree/master/output/trained_weights). @yangxue0827 @yangJirui