James-Andrew R. Sarmiento comments

Results 92 comments of


                                            James-Andrew R. Sarmiento

Converting to NVLabs stylegan2-pytorch or stylegan2-pytorch-ada

@james-oldfield Unfortunately, I went with a different approach but you can possibly do that. I just restructured the code to make it a bit similar to NVLabs's version where there...

How do I use the pretrained models to generate multiple images using a prompt?

I still do not understand it. Say, I want to generate 1K images of 'a red square at the left of yellow ball'. How do I do that?

Validation is not in the size of indicated img-size

seems like it has something to do with the `rect=True` here https://github.com/meituan/YOLOv6/blob/435cf0f9a89f6d3f63a48174164731cb1e646c50/yolov6/core/engine.py#L339-L342

Validation is not in the size of indicated img-size

Yeah i added that. it doesnt work and still has a different resolution when validating because rect is True

Validation is not in the size of indicated img-size

my dataset is not NxN

Resume command Doesn't Work

This. It should be fixed

Insights on why area=medium for custom dataset is very low?

@mtjhl I have a custom dataset

What does num_layers mean and how to deal with a feature extractor that has 4 feature pyramid outputs?

@mtjhl i am trying to use a backbone in replacement of YOLOv6's backbone that contains 4 pyramid layers instead of three. Any advise on how to modify the PANNeck to...

Where is best spot to add albumentations augmentation?

Yes. But where in that spot should I put something like `images, labels = self.albumentations(...)`

What is the reason why Swin-T only outputs features 1,2,3 and not 0?

Does that mean I can specify four output features? it seems like YOLO only takes three. is there a better way to use all features with YOLO without loss of...