DeepHash icon indicating copy to clipboard operation
DeepHash copied to clipboard

Published 20 hours ago • verified publisher icon thulab

DCH: low results

Open hbellafkir opened this issue 4 years ago • 3 comments

I trained DCH on COCO using the default parameters in val_train script, which sets the iter_num to 2000. The results too low compared to the paper:

iter 33 prec 0.3673785145624646 rec 0.9312258941859837 mAP 0.4742411791076638 i2i_by_feature 0.5373119936770314 i2i_after_sign 0.48951766955994036 i2i_prec_radius_2 0.44337251780011877 i2i_recall_radius_2 0.6585969771414468 i2i_map_radius_2 0.518241127343017

Did i miss something the configuration file?

hbellafkir avatar Sep 12 '20 14:09 hbellafkir

Did u find the missing configuration? If you find, could you share your hyperparameter setting? I also think there's something missing.. e.g., the default value of the quantization loss parameter(q_lambda) is set to 0.

fegler avatar Sep 15 '20 12:09 fegler

No i didn't. I'm still waiting for a answer. Yes I noticed that too, q_lambda is set to 0 not only in DCH, but also in DTQ.

hbellafkir avatar Sep 15 '20 12:09 hbellafkir

No i didn't. I'm still waiting for a answer. Yes I noticed that too, q_lambda is set to 0 not only in DCH, but also in DTQ.

Hi! Could you help me please? I'm beginner in DL and have no idea how to test model I have trained. Model is somehow saved in .npy format. Don't know how to work in such a format therefore can't put bunch of my test images to test the CBIR model :(

sacralitus avatar Nov 06 '20 07:11 sacralitus