Ashwin

Hey @glenn-jocher thanks for your response. How important is it to change this if we move from 640 -> other image sizes?? `b.data[:, 4] += math.log(8 / (640 / s)...

@glenn-jocher thanks for your insights. I am trying out with a large number of anchors while keeping `anchor_t=4.0` Here is what I am seeing with the default anchors the fit...

> In order to facilitate verifying if an image augmentation method does what it is supposed to do, I added the section _Image augmentation_ to the notebook _inspect_balloon_data.ipynb_ in my...

> Sorry, not a response to your question : Were you able to train on the provided dataset? For me I get the max recursion error and if I change...

> @AshwinAKannan - which dataset format did you use for your custom dataset? I am using CULane dataset format

@mindmad my code is derived from llamas.py (lines 115 to 121). Here's is what it looks like (modify load_annotation function. It'll create seg map on the fly) if mask_path and...

> @CuthbertCai Thanks for your quick reponse. > original version means caffe version of this paper ? > I found DANN implemented with [tensorflow. [https://github.com/pumpikano/tf-dann] > In this repo, they...

Hello, I ran an experiment for 1000 epochs with a slight change in model - removed batchnorm layers. The idea was to have a model similar to what is mentioned...

embedding with 1024 points (epoch ~400):  Noticed that MNIST results mentioned in the paper don't form distinct clusters either.

> 1. **Handling of Background Class**: YOLOv5 does not explicitly infer a 'background' class during training or detection. If you're seeing a 'background' class in your confusion matrix, it might...