RealtimeStereo
RealtimeStereo copied to clipboard
JiaRenChang
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
Hi, thanks for sharing your work. I wanted to test the model with CPU inference but the hardcoded .cuda() calls were preventing that, so I replaced them with .to(device), making...
Hi, I meet an issues: Traceback (most recent call last): File "finetune.py", line 205, in main() File "finetune.py", line 179, in main test_loss = test(imgL,imgR, disp_L) File "finetune.py", line 140,...
Hello， thank you for your excellent work！！！However，can you provide the pretrained model in baiduyun？
3D CNN
Hello, I want to know where the relevant codes of 3D CNN are? I don't seem to have found it.Thank you.
Hi @JiaRenChang, I was working on AnyNet (https://github.com/mileyan/AnyNet) project, but haven't got appropriate results because I was not able to compile SPN module successfully (Error while running make.sh: Not able...
what batch_size did you choose to test your model latency on TX2? Did you test with a larger batch_size and calculate the latency by factorizing the batch_size or you just...
Sorry to disturbe you again.. I notice that you do crop during training and crop the image to 288x576. I think this operation will lose the feature outside the 288x576,...
The work, FDSCS, also provides a low GPOS model, please see https://github.com/ayanc/fdscs, while your paper doesn't mention it.
The SecenFlowLoader.pyc cannot be imported in google colab environment for some reason can you please provide the .py file before compiling and if that would make any difference if I...
Hello, Thank you for this repo, the model is amazing. I was wondering if you ever converted this model to a tensorRT engine. I tried to do this, and was...
Metadata
Owner
Metadata
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)