Ning Ding

@cloudyszz I have looked through the source code of im_detect in the [lib/fast_rcnn/test.py](https://github.com/sanghoon/pva-faster-rcnn/blob/master/lib/fast_rcnn/test.py#L113) and found that it is different with [the original version in py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn/blob/96dc9f1dea3087474d6da5a98879072901ee9bf9/lib/fast_rcnn/test.py#L108). Maybe you could try the...

The code for the Market 1501 part still remained old version, sorry for my late update, I just suffered a tough month with too many projects. I'm planning to add...

Hi, it's my pleasure to share the work. I have updated the model definition script last night, you could use the latest version Keras to define the model now. Today...

Hi, to estimate how many iterations the model should be trained for this task is different with what you think. First, though the total images of the CUHK03 dataset are...

There may be a formula to compute the number of iterations but I don't know what it is. In my opinion, at least let the model see every instance 5-20...

@gliese581gg Thank you for your work! I have add a `MIT LICENSE` to the repo and I'll update the whole project to TensorFlow in about two weeks. Keep in touch!

Try with the Python 2.7 for the error mentioned. If you could wait a few days, I will solve the second problem to stop and continue next time. I'm planning...

Ok, I will retrain a model this week, and share the model on the google drive.

Sorry, the code for Market 1501 has not been updated yet. I just suffered from some really busy weeks. Now I got some time and would continue to update the...

Try running the command `python create_dataset.py --mat $abs_path_to_your_cuhk03.mat` The info shows you gave the script a wrong file path to the `cuhk03.mat`.