harsh-99 / SCL

Implementation of "SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses"

harsh-99/SCL Issues

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
Updated 7 months ago
ImportError: No module named cython_bbox
Updated 10 months ago1
Using multilple GPUs to accomplish distributed training
Updated a year ago1
About cityscape-->foggy cityscape test set
Closed 2 years ago
About sim10k dataset
Closed 4 years ago2
Heat Map
Updated 2 years ago
question of t-sne
Updated 3 years ago
after filtering, there are 0 images
Updated 3 years ago1
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.
Updated 3 years ago1
About the trained model.
Updated 3 years ago1
Your implementation of domain adaptive faster rcnn performs better than paper values, what might be the reason?
Updated 3 years ago1
Run trainval_net_SCL.py with custom dataset raises RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0.
Closed 4 years ago4
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
Closed 4 years ago
about INIT dataset
Closed 4 years ago1
Applying SCL on SSD
Closed 4 years ago1
About cityscape and foggy dataset
Closed 4 years ago3
Can I run this Solution in real time or without the need to train the target data
Closed 4 years ago3
How to do Object detection on target domain(ex: Clipart) that don't have annotation.xml label
Closed 4 years ago2
Can this method be used as unsupervised object detection, if yes then how to do object detection on unlabelled target domain data
Closed 4 years ago4
Import Error
Closed 4 years ago5
visualization of features from PASCAL to Clipart
Closed 4 years ago1
preparing clipart dataset problem and multigpu training
Closed 4 years ago3
Experimental details
Closed 4 years ago1
did you tried with EfficientNet?
Closed 4 years ago
Your implementation of da-faster-rcnn seems very different from the original paper, right?
Closed 5 years ago3
How do I use cityscape and foggy cityscapes datasets?
Closed 5 years ago4
what is the difference between strong-weakly detach method with your proposed Gradients Detach Updating?
Closed 5 years ago1
How many epochs should I train?The default is 20. Is that too many?
Closed 5 years ago1
how to train this model
Closed 5 years ago9
dataset of clipart
Closed 5 years ago2