HDC.caffe

HDC.caffe copied to clipboard

Hi @PkuRainBow , thanks for open sourcing your work. I want to test the PKU-VehicleID dataset with your method but can't find the corresponding instruction or code. Can you help...

jonbakerfish

https://github.com/PkuRainBow/Hard-Aware-Deeply-Cascaded-Embedding_release/blob/e2f5462aab0ed1c9d6a85503bf7d42eac632d5b1/src_code/test_deep_fashion.py#L29 Hi, I was wondering how you calculated the recall. In fact, in your code, if you query K images and once you get one correct, and this is a...

XiaodanLi001

Why do you change initial GoogleNet loss1 output from 1000 to 128? Also,why do you change the lr_mult simultaneously ?

3

jsjs0827

How to extract feature

2

Sorry, i can't extract the feature after traning the model. "../bin/extract_feature.exe" is not found. Can you tell me how to do it?

XinyiXuXD

Would operation system differ the result?Windows or linux?

2

I trained your model with linux, then I use the "loss3/classifier" layer to extract the feature of the same pictures both in windows and linux, the feature differs.Why? I just...

jsjs0827

warning: ‘auto’ changes meaning in C++11; please remove it [-Wc++0x-compat]

1

When I make all -j16 with Ubuntu，the problem happens.What should I do?

jsjs0827

jsjs0827

my trained model cannot achieve the same performance compared with the provided trained model

6

I use the default training setting in the code. For StanfordOnlineProduct dataset I got: stanford online products mean recall@ 1 : 0.632077 stanford online products mean recall@ 10 : 0.785517...

pipipopo

About test CARS196

4

Hi, I have a problem when test CARS196. Would pls. help me? Traceback (most recent call last): File "hdc_test.py", line 126, in main(sys.argv[1:]) File "hdc_test.py", line 55, in main data_cnt,...

anshan-XR-ROB

Why Recall@K is equal to zero

1

I try to execute the command " python hdc_test.py -d cars196 -c HDC" using the model trained by you. But in the script hdc_test.py, when choose HDC method, the function...

gobigrassland