Eric Nguyen

Hi, thanks for the repo, it's great! I was curious if this repo includes the 21-way Contextual ARC, or is this only the Naive ARC approach? I believe the contextual...

Training doesn't work / converge for Blender - chair dataset

1

Hi, I followed the install instructions and tried training for the chair data in Blender. However, it never converged and just output white background. The PNSR just bounced around between...

Cosine decay schedule changes with different accumulate_grad_batches values

1

When using the accumulate_grad_batches flag in a Pytorch Lightning trainer, I noticed it changes my scheduler LR differently. I am using TIMM's cosine decay scheduler. And when I use 1...

Hi! I'm looking to do inference only, and not retrain. Would anybody be willing to share their model parameters that was trained on ImageNet or similar full size images (COCO,...

Hi! I'm looking to do inference only, and not retrain. Would anybody be willing to share their model parameters that was trained on ImageNet or similar full size images? (Preferably...

Slow dataloading every N batches, where N=num_threads

2

I’m trying to train a 3D resnet model for classification, but the training time is doing something weird. I have 28 cpus, and 28 num_workers for dataloading, and so every...

Progressive learning in codebase?

1

Hi, I see a number of people asked questions about where the code for progressive learning was located exactly in the repo. I also couldn't find it. I was wondering...

How can I get the depth image into 16uc1 format?

4

Hi, I'm generating depth map images in .png from an Intel Realsense camera, but I can't seem to get the format to match the 16uc1 format. I originally had a...

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xdd in position 112: invalid continuation byte

3

Did anyone else get this error as well? Is it an international text thing? I'm in the US. UnicodeDecodeError: 'utf-8' codec can't decode byte 0xdd in position 112: invalid continuation...

Are there any pretrained hashing models that were trained on ImageNet or similar?

1

Hi! I was wondering if there were any pretrained models to compute image hashes that were trained on ImageNet or similar (coco, NUS-WIDE, etc). I saw on this repo that...