zlmzju / part_reid Goto Github PK

Firstly, thanks your great work!
but i cannot use your python layer to train my model. it will stop when cv2 reading one image.
could you give me some help about this?
thanks

Hi @zlmzju,

What is the license?
Thanks

make: *** [.build_release/src/caffe/layers/online_triplet_loss_layer.o] Error 1

src/caffe/layers/online_triplet_loss_layer.cpp: In member function \u2018virtual void caffe::OnlineTripletLossLayer::Forward_cpu(const std::vector<caffe::Blob>&, const std::vector<caffe::Blob>&)\u2019:
src/caffe/layers/online_triplet_loss_layer.cpp:100:27: error: \u2018>>\u2019 should be \u2018> >\u2019 within a nested template argument list
vector<pair<Dtype, Dtype>> min_max_distances;
^
src/caffe/layers/online_triplet_loss_layer.cpp: In instantiation of \u2018void caffe::OnlineTripletLossLayer::Forward_cpu(const std::vector<caffe::Blob>&, const std::vector<caffe::Blob>&) [with Dtype = float]\u2019:
src/caffe/layers/online_triplet_loss_layer.cpp:287:1: required from here
src/caffe/layers/online_triplet_loss_layer.cpp:70:13: warning: unused variable \u2018dim\u2019 [-Wunused-variable]
const int dim = bottom[0]->count() / num;
^
src/caffe/layers/online_triplet_loss_layer.cpp: In instantiation of \u2018void caffe::OnlineTripletLossLayer::Forward_cpu(const std::vector<caffe::Blob>&, const std::vector<caffe::Blob>&) [with Dtype = double]\u2019:
src/caffe/layers/online_triplet_loss_layer.cpp:287:1: required from here
src/caffe/layers/online_triplet_loss_layer.cpp:70:13: warning: unused variable \u2018dim\u2019 [-Wunused-variable]
Makefile:581: recipe for target '.build_release/src/caffe/layers/online_triplet_loss_layer.o' failed
make: *** [.build_release/src/caffe/layers/online_triplet_loss_layer.o] Error 1

Hi!
Do you have or can you recommendation any pytorch or tensorflow implementation of your paper?
Thank.

In the extract_features method in the Extractor() class, there is a line:

normed_features=self.net.blobs['normed_feature'].data.copy()

I checked the _caffe.cpp file in ./caffe/python/caffe/_caffe.cpp and I then checked all the properties for net.blobs and 'normed_feature' was not one of them.

Any ideas on how to resolve this?

Thanks

From the readme - it seems that the train.sh script is missing in the train folder. I am looking for if it is possible to get the training script for replicating and improving by tuning hyperparameters.

Hello, I want to down load the dataset. But there is a warning that "this page is asking you to confirm that you want to leave - data you have entered may not be saved". How can I down load the dataset?

您好，感谢您的代码，我在试着跑你的demo时，出错了：

但是我在vs 2013中直接调用模型文件不会出错，请问这是为什么呢？

I am try to reproduce the results on market1501. But the triplet loss is very small, nearly to zero. So after iter=35000+, the network did not update(loss=0). I can't reproduce the results(R@1:81%,mAP:63%), but get lower results (R@1:76%,mAP:55%).
Have you met this situation? What's the possible reasons ?

how about your gallery and probe ?
and training data