Tarun Narayanan

I've been training my own MODNet models on custom data, using the configs provided. How do I use the model checkpoint provided in the readme [HERE](https://paddleseg.bj.bcebos.com/matting/models/modnet-hrnet_w18.pdparams) as a starting point...

Train in batches : PyTorch models

2

Hey, I'm a beginner to active learning and I'm just trying to implement modal along with a standard PyTorch softmax classifier using the skorch api as instructed in your documentation....

Add a different backbone other than Mobilenetv2?

3

Hey, great work on MODNet! I'm looking to try out modnet with a HRNet backbone for better results. Would you happen to already have the model function for HRNet that...

Dataset structure

15

Hi I'm having a little trouble understanding the dataset structure that I should follow in order to be able to train with this package. Is it one parent folder, one...

Loss saturates

1

I tried training SimCLR on CIFAR10 with the exact config that you've provided in the docs, except a 128 batch size, and without SyncBN since I'm running it on Colab....

start_document_analysis does not support List of Images

2

start_document_analysis in the documentation says it supports a list of PIL images, but in the source code https://github.com/aws-samples/amazon-textract-textractor/blob/e40f5b0378f9ee24d0a757de414505fb06a4471f/textractor/textractor.py#L488 it only accepts a string, a bytearray, or a PIL Image. How...

Hey, I really liked your implementation of the Adapting Grad-Cam for Embedding Networks paper. Your code makes understanding the application a lot better! I have some ground-level doubts about your...