yanxp / ssm-pytorch Goto Github PK

I found what is probably just a typo in trainval_net.py. the right variable might be im_boxes.

Traceback (most recent call last):
  File "/home/riccardo/SSM-Pytorch/tools/trainval_net.py", line 267, in <module>
    ss_avg_score.append(ss_accum_score/len(img_boxes))
NameError: name 'img_boxes' is not defined

Hi,
Can I clarify did you train fast-rcnn or faster-rcnn? Because the base repository https://github.com/ruotianluo/pytorch-faster-rcnn is for faster rcnn?

Hi @yanxp, thanks for your nice work. will you include the RFCN experimental part in this code? As I can see, it only include roi_pool for faster rcnn. Looking forward to your reply.

Hi yanxp,

Recently I am reading the paper Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection and the code implementation.

I have some questions about the AL process part which seems a little different between the code and the paper description.

In my understanding, the framework above in the paper shows the image whether require user annotating (AL process) depends on the prediction consistency score from image cross validation. So it means do image cross validation firstly...

But in the code, it seems a little different....

In my understanding, the AL part just depends on the function judge_uv (cls loss), but not related to image cross validation.....

So image cross validation just works for SS part?

Maybe I misunderstood... could you help me please, thanks!

Which Cuda toolkit version did you use? Thanks

Hello there, I am trying different things with the code.

I encountered the following error:

Traceback (most recent call last):
  File "./tools/trainval_net.py", line 236, in <module>
    v,v_val = judge_uv(loss,gamma,clslambda)
  File "/home/riccardo/SSM-Pytorch/tools/../lib/utils/help.py", line 135, in judge_uv
    if(lsum > threshold):
NameError: name 'threshold' is not defined

Could you please provide some suggestions on this? Thank you.

hello
when I run the code, it shows missing files.

The error message is as follows.
ModuleNotFoundError: No module named 'nms._ext.nms._nms'
ModuleNotFoundError: No module named 'layer_utils.roi_pooling._ext.roi_pooling._roi_pooling'

Could you supply me with these two documents?

Which Torchvision version did you use? Thanks