yanxp / ssm-pytorch Goto Github PK
View Code? Open in Web Editor NEWTowards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection
License: MIT License
Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection
License: MIT License
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
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.