princeton-vl / pose-ae-train

Training code for "Associative Embedding: End-to-End Learning for Joint Detection and Grouping"
BSD 3-Clause "New" or "Revised" License
373 stars 76 forks source link

Unable to replicate the results with the pretrained model #52

Open mohitiitb opened 4 years ago

mohitiitb commented 4 years ago

Hi @anewell,

The evaluation of the pre-trained model is not producing the expected results. The mAP results for the single and multi-scale settings on the pretrained model are 0.107 and 0.154, which is far less than the expected output of 0.59 and 0.66. The mAP evaluation for a model trained from scratch(for 100 epochs with batch-size 8) is similarly producing poor results, mAP score of 0.137 on the multi-scale evaluation setting.

Thanks!

PS: Adding Arjun and Rishabh to the thread. @stencilman @rishabhdabral

MehwishG commented 4 years ago

Hi I am also facing the same issue. I have tested the pretrained network on coco 2017 dataset. It's not giving results as reported in paper. Did you solve it? please reply @mohitiitb