Comments (10)
In the make_cam.py file, https://github.com/jiwoon-ahn/irn/blob/master/step/make_cam.py#L42, why highres_cam and strided_cam use different unsqueeze dimension, for I think this doesn't make any difference?
from irn.
Hi @zhaohui-yang,
- It is common practice. Please refer to Sec 6.1. of the paper.
- Yes, they are the same.
from irn.
@jiwoon-ahn Thanks, you solved my questions. Besides, in the resnet50_cam.py, the x is detached after passing the layer2, which means the variable x would not BP the gradients. However, in the train_cam.py, the parameters in layer1 and layer2 are packed in the backbone (trainable_parameters), which are also included in the PolyOptimizer. I wonder if you update the parameters in layer1 and layer2, also the bn weight and bias?
from irn.
Will the mean shift introduce the gap between training and var? This layer inherits from BatchNorm2d. During training, x' = (x - mean)/std, however, during inference, x' = x - mean, which is different from training. What is the reason for the difference?
from irn.
- All parameters including the BatchNorms in layer1 and layer2 do not receive gradients, thus they are not updated.
- During training, MeanShift layer stores the moving average and returns the input itself. It means that the layer acts as an identity function, where the update of the moving average is simply achieved by calling BatchNorm.
from irn.
Thank u for your patience. By the way, is this the final version code? I have run this code for three times, which achieves 35.8, 36.0 and 36.2 mAP for instance segmentation (lower than 37.7 in Tab.1). The only thing I changed is I half the batch size while training the irn because of the GPU memory. So I wonder if this code would guarantee an mAP around 37.7 if I use larger batchsize?
from irn.
I have confirmed this code alone can reproduce the reported results. Please try with different hyper-parameters.
from irn.
Must be my problem. Thank you!
from irn.
@jiwoon-ahn What kind of GPU do you use? P100 or V100? For my Titan with 12G could not fit in the batchsize=32 for train_irn. I modified the code to fit for Parallel training, but encountered the same problem with issue #13 .
from irn.
@zhaohui-yang,
Please refer to this comment. #13 (comment)
Thanks.
from irn.
Related Issues (20)
- Would you share the weights of IRNet for generating the pseudo label?
- Inter-pixel relation mining. Point neighborhood.
- About 'x = x[0] + x[1].flip(-1)' in resnet50_cam.py. HOT 3
- using own dataset HOT 2
- How to apply CRF postprocessing at final stage, after making sem_seg_labels?
- cam_to_ir_label HOT 2
- Help For the CAMs
- For comparison with AffinityNet implementation details in your paper
- about the search indices HOT 1
- about the function of “Instance Map”
- On the number of convolutional filters in IRNet
- Time cost of generating one pseudo instance mask
- About the visualzation of edge map HOT 1
- About every time the results are unstable
- sqrt in CAM
- Training is so slow after first epoch
- run_samples.py ValueError HOT 1
- How to adjust the value of 'conf_fg_thres' 、’conf_bg_thres‘ 、’beta‘ and 'exp_times' HOT 1
- int32 error
- CAM_to_irlabel and train_irn
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from irn.