Miguel Campos Romero

Results 44 comments of Miguel Campos Romero

Gaussian noise and Gaussian blur are different as I am showing below. As I said, Gaussian noise is used in several unsupervised learning methods ![image](https://user-images.githubusercontent.com/37028633/175263048-a14cb4f3-7388-4cf0-b98c-1ff14728b090.jpeg)

That will the job for now

The error is because the json hasnot the correct path to the images. That’s why. I solved this issue in mu computer

Sorry, i am meaning, if we are doing inferences with a trained model on a folder with images, why are we using the(for instance) cfg/coco.data? In yolo documentation is enought...

I'm also developing the fastflow model. I have a WIP version that gets near results (- 0.5). It's difficult replicate because paper has incongruences and It doesn't provide implementation details....

Thanks for your answer. Yes it's so hard to achieve the results. I'm trying different kind of losses but can't achieve the results. My best is 98,6 in detection and...

Hello @narendasan I will organize the answers: **+ It would help if you could turn on debug logging** This is how ends the code of my foward method ``` all_likelihoods...

Is there any update about this? - `torchvision.transforms.gaussian_blur` inside the forward method raises error? - How can I use `torch_executed_modules`? Documentation about it is very poor Thanks