CSP
CSP copied to clipboard
liuwei16
High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection, CVPR, 2019
Hi~ I ran the test_wider_ms.py with one GPU but it's too slow. Even if I set `os.environ["CUDA_VISIBLE_DEVICES"] = "0, 1, 2"`, there is still only one working GPU, the memory...
Hi, I have a question about the NMS post-processing. For example, why not try sigmoid activation function at the end of the network and get a heatmap with prob between...
from nms.cpu_nms import cpu_nms can't import correctly. so i wonder how to compile in your code, and can you show the makefile @liuwei16
Epoch 1/150 get_batch_gt: 'NoneType' object has no attribute 'shape' get_batch_gt: 'NoneType' object has no attribute 'shape' get_batch_gt: 'NoneType' object has no attribute 'shape' get_batch_gt: 'NoneType' object has no attribute 'shape'...
I test one image, but result is so bad. There are so many false-positive samples. Why?  
when I try to extract the dataset "caltech"in matlab, I've got the problem Undefined function or variable 'int2str2' Error in dbExtract (line 37) fs=cell(1,n); for i=1:n, fs{i}=[f 'I' int2str2(i-1,5)]; end...
after we follow these steps to get the results, the average of results is the final MR that mentioned in the paper? or the minimum in the result is the...
Great work! thank you for your code. I have a question about seman_map. `seman_map[:,:,1] = 1` [https://github.com/liuwei16/CSP/blob/785bc4c5f956860116d8d51754fd76202afe4bcb/keras_csp/data_generators.py#L23](url) But in [https://github.com/liuwei16/CSP/blob/785bc4c5f956860116d8d51754fd76202afe4bcb/keras_csp/data_generators.py#L39](url) `seman_map[y1:y2, x1:x2,1] = 1` , is there have a bug?
@liuwei16 Hi, thanks for your research. In ```generate_cache_city.py```, you cache boxes with label=1 and height >= 50, but do not consider the occlusion level, that means you are not using...
Hello, have you trained the person in the COCO data set, and what is the training result?
