You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I put the trained model under output/model_dump/COCO, images from 2017 Test images under data/COCO/images/test2017, COCO annotation 2017 Testing Image info under data/COCO/annotations. Also, made the changes in data/COCO/dataset.py regarding input_pose_path and main/config.py about testset and dataset as you explained at this issue.
The tensorflow version is not stated in requirements.txt, therefore I tried with tf 1.9, 1.10 and 1.11. Also tried both python test.py --gpu 0-1 --test_epoch 140 and python test.py --gpu 0 --test_epoch 140. Unfortunately, I could not make it work.
Any suggestions?
The text was updated successfully, but these errors were encountered:
Btw, I switched to another data you mentioned here and which does not have bbox attribute. Since the name contains 256x192, I also changed input_shape at main/config.py but I faced the same errors.
Sorry it has been few years since I wrote this code, so it is hard for me to get the reason quickly. Please make sure at here whether you load the annot and input_pose correctly.
I am facing 2 errors like here and here when I want to test the pre-trained model on name_of_input_pose.json you provided.
I put the trained model under
output/model_dump/COCO
, images from 2017 Test images underdata/COCO/images/test2017
, COCO annotation 2017 Testing Image info underdata/COCO/annotations
. Also, made the changes indata/COCO/dataset.py
regardinginput_pose_path
andmain/config.py
abouttestset
anddataset
as you explained at this issue.The tensorflow version is not stated in
requirements.txt
, therefore I tried with tf 1.9, 1.10 and 1.11. Also tried bothpython test.py --gpu 0-1 --test_epoch 140
andpython test.py --gpu 0 --test_epoch 140
. Unfortunately, I could not make it work.Any suggestions?
The text was updated successfully, but these errors were encountered: