New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ImportError: No module named 'inplace_abn' #141
Comments
Any help please... |
The HRNet small model is trained based on Pytorch-v1.1 and official sync-bn is used (inplace-abn is not used here). You can try our pytorch-v1.1 branch. |
@sunke123 Many thanks, I will give it a try! Just a couple more questions :
The addition of OCR & Segfix would improve the accuracy of "HRNetV2-W18-Small-v2" further?
Comparison of mIOU on Cityscapes.
Why is U-HarDNet-70 at the top of paperswithcode SOTA list for real-time segmentation? I am looking to implement high-quality semantic segmentation on a mobile device for accurate human segmentation for still images (i.e. non-realtime). Would "HRNetV2-W18-Small-v2" be a great option for this? |
I tried pytorch-v1.1 branch and installed the following exact configuration 👍 PyTorch=1.1.0 I am still getting same error "No module named 'inplace_abn'" while training You said
but in this file, I noticed that "inplace_abn" is imported
Do I need to do any changes here? |
@InternetMaster1
I think that HRNet is a good choice. |
@InternetMaster1 I think you can implement HRNetV2-W18-Small-v2 + OCR by overriding You may also need to override SegFix is another standalone post-processing mechenism. You can find its usage in our openseg repository. |
Thank you for the plethora of information! Yes, HRNet looks like an awesome option for our needs!
Can you be more specific? Along with deletion of the folder, do I need to even make any changes in any py files? Sorry for the newbie question, but I am stuck at installation
|
Many thanks for the detailed informtion. Once my installation is successful, I will check out the OCR option!
|
InplaceABN is not used in the code of the Pytorch v-1.1 branch. The lightweight segmentation work is submitted to a CV conference. By the way, the author of lightweight hrnet tell me that you can try our HRNetV2-W18-Small-v2. It's actually a good choice. |
I was able to finally get it! I was trying to use clone method from the pytorch-v1.1 branch. The URL for clone of the branch is same as the main repo, and hence the confusion! I had to use the Download functionality to get the code for the branch Thanks |
If you get a chance, could you reply to the following, many thanks in advance
|
How to convert the final model file to make it work on mobile, mainly Android?(i.e. tensorflow lite or ncnn). Are there any special steps involved? I don't have any experience with HRNet and your guidance would be most helpful Many thanks! |
Hi I found 1.1 branch actually use batchnorm2d, I guess it is not syncnorm. Dose it mean no difference? |
@ywang370 No. We use nn.SyncBatchNorm for PyTorch 1.1. See here. |
I also have no experience with the mobile application. |
I tried Image Segmentation using the " HRNetV2-W18-Small-v2 " small model with cityscape dataset.
I haveinstall all modules mentioned in requirement.txt file with the matching version of the modules.
My config is as follows -
python 3.6
cuda 9.2
ninja 1.8.2
pytorch 0.4.1
I had done the steps till data preparations and then I tried to train using following command,
python tools/train.py --cfg experiments/cityscapes/seg_hrnet_w18_small_v1_512x1024_sgd_lr1e-2_wd5e-4_bs_12_epoch484
I am getting the below error.
To solve this, I have tried with diff version that match with ninja and cuda, but no luck. Any help please!
The text was updated successfully, but these errors were encountered: