Comments (4)
Hi, I think it's data loader problem so it should be coming for both scl and strong-weak. Maybe you should try to find for which data point exactly this problem is coming. And for training strong-weak which code did you use?
from scl.
@harsh-99 I used the strong-weak code in this repository. Just with:
CUDA_VISIBLE_DEVICES=$1 python trainval_net_global_local.py --cuda --net vgg16 --dataset mydataset_source --dataset_t mydataset_target --gc --lc --save_dir output
from scl.
I've figured it out. The SCL do not support batch size other than 1. Because if batch size = 2, "pooled_feat" will add 256 channels after each one in "feat1, feat2, feat3". This will cause a shape mismatch in "netD_inst" because the channels are hard-coded like 2048+128+128+128. So I just changed the cfgs and train it for a longer time. Still appreciate your great work!
from scl.
@SkeletonOne Thanks a lot for pointing out that. I will try to add the functionality of batch size greater 1. In case if you have done that, feel free to send PR.
from scl.
Related Issues (20)
- Experimental details HOT 1
- visualization of features from PASCAL to Clipart HOT 1
- Applying SCL on SSD HOT 1
- Can this method be used as unsupervised object detection, if yes then how to do object detection on unlabelled target domain data HOT 4
- How to do Object detection on target domain(ex: Clipart) that don't have annotation.xml label HOT 2
- Can I run this Solution in real time or without the need to train the target data HOT 3
- About cityscape and foggy dataset HOT 3
- Can i generate or train model using this method and run it on different dataset/images that is similar to target domain data but this new dataset don't exist in target domain data when it was trained
- How can I add custom new class labels, lets say-x classes to a SCL trained model( which is already trained on y classes). So I do not replace those y classes and in total I have x+y class labels. HOT 1
- About sim10k dataset HOT 2
- Your implementation of domain adaptive faster rcnn performs better than paper values, what might be the reason? HOT 1
- About the trained model. HOT 1
- after filtering, there are 0 images HOT 1
- question of t-sne
- Heat Map
- About cityscape-->foggy cityscape test set
- Using multilple GPUs to accomplish distributed training HOT 1
- ImportError: No module named cython_bbox HOT 1
- File "/home/lty/anaconda3/envs/SWDA/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward self.padding, self.dilation, self.groups) RuntimeError: cublas runtime error : the GPU program failed to execute at /opt/conda/conda-bld/pytorch_1525909934016/work/aten/src/THC/THCBlas.cu:249
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 scl.