HCPLab-SYSU/SSGRL

coco map is 0.037 in epoch15

valencebond opened this issue · 8 comments

valencebond commented

i just run the code according to readme file and adjust it to pytorch1.1, python3.6.
Is there something should be changed?

Mu-xsan commented

I run it in the environment of PyTorch 0.4.1, Python 2.7.
I updated one dataset interface in utils/transform.py, but I already set it in the script of each dataset. You can just update it and try again.
In MS-COCO, I used cocoapi to load the data, have you used this?
You can read the datasets/cocodataset.py to learn how I load those data, just a few sentences.

KiAkize commented

i just run the code according to readme file and adjust it to pytorch1.1, python3.6.
Is there something should be changed?

I adjust model to ResNet50/ResNet101. CoCo mAP is still 0.037 :(

phython96 commented

i just run the code according to readme file and adjust it to pytorch1.1, python3.6.
Is there something should be changed?

I adjust model to ResNet50/ResNet101. CoCo mAP is still 0.037 :(

I got mAP 0.037 too.

zjhdxh commented

i just run the code according to readme file and adjust it to pytorch1.1, python3.6.
Is there something should be changed?

I adjust model to ResNet50/ResNet101. CoCo mAP is still 0.037 :(

I got mAP 0.037 too.

I got mAP 0.037 too.

phython96 commented

i just run the code according to readme file and adjust it to pytorch1.1, python3.6.
Is there something should be changed?

I adjust model to ResNet50/ResNet101. CoCo mAP is still 0.037 :(

I got mAP 0.037 too.

I got mAP 0.037 too.

I solve the problem.You have to run with python 2.7 and pytorch 0.4.Then the mAP flies.

jasonseu commented

I got mAP 0.037 too.

i just run the code according to readme file and adjust it to pytorch1.1, python3.6.
Is there something should be changed?

I adjust model to ResNet50/ResNet101. CoCo mAP is still 0.037 :(

I got mAP 0.037 too.

I got mAP 0.037 too.

I got mAP 0.037 too.

student-petercai commented

I got mAP 0.037 too.

Yeah it's weird but true

NC122 commented

i just run the code according to readme file and adjust it to pytorch1.1, python3.6.
Is there something should be changed?

How did you solve it in the end