Yong Yuan

I also faced the problem when I run the Matlab version. The error is as follows: ``` sh Undefined function or variable 'mex_pb_parts_final_selected'. Error in det_mPb (line 6) textons, ......

@bear63 I also faced the problem, the error is as follows: ```text in () ----> 1 partImg = dumpRotateImage(im,degrees(atan2(pt2[1]-pt1[1],pt2[0]-pt1[0])),pt1,pt2,pt3,pt4) TypeError: only length-1 arrays can be converted to Python scalars ```...

After updated the `other.py` file, it ran success on my laptop. Thanks.

@kylinXu I followed this [mAP computation](http://yongyuan.name/blog/evaluation-of-information-retrieval.html) to get the mAP score. The mAP computation shows in the post is very clear. I hope the figure in the post helps you...

It's true, thank you for point out the potential risk. I'll check out it today.

It depends on your task, instance retrieval or similar retrieval. For similar retrieval (category retrieval), it's really OK.For instance retrieval, you might be interested in [cnn-cbir-benchmark](https://github.com/willard-yuan/cnn-cbir-benchmark). There are some references...

If you don't want to labeled so many pictures, you can choose method based on local feature. [flickrdemo.videntifier.com](http://flickrdemo.videntifier.com/) is a demo based on SIFT feature. The performance is really promising.

@frkhit Is the code compatible with Python 2.7?

Changing the [train.py#L164](https://github.com/wujiyang/Face_Pytorch/blob/master/train.py#L164) of `exp_lr_scheduler.get_lr()[0]` to `optimizer_ft.param_groups[0]['lr']` will fix the bug.

@kjsman I think you should use the `outs[0].flatten()` as input, and NeuralHash is an embedding network which put out the `outs[0].flatten()` of 128 dimension. The `seed.dot(outs[0].flatten())` is the Local Sensitive...