Amit Agarwal

Datasets for Benchmarks

2

Thanks for opensourcing the code base. The paper was really insightful and I was looking to conduct few experiments, is it possible to share the code used for adding the...

Edge Embedding Not updated by Every GNN Layer

5

https://github.com/open-mmlab/mmocr/blob/64fb6fffc06f168355c8e3d28f5b31f26536f485/mmocr/models/kie/heads/sdmgr_head.py#L82 The GNN Layers return node embedding and edge embedding . But the edge_embedding is name as cat_nodes. That is the updated edge embedding is not going as input to...

Hi @naiveHobo ! Are there any particular changes in the model compared to what is mentioned in Attend,Copy & Parse paper ?

KeyError while using compare_to_groundtruth

4

Hi, I am was trying to generate results on MOT16 challenge results and used mm.utils.compare_to_groundtruth to get the accuracy but resulted in error. ``` df_gt = mm.io.loadtxt('MOT16/preds/MOT16-01/gt/det.txt') df_test = mm.io.loadtxt('MOT16/preds/MOT16-01/gt/pretrained_pred.txt')...

Hi Team, are we looking for any update here ?

In the paper it's mentioned that from the automatically learned representations , clustering is done on real images. Can you please show or direct,e to the example/code used for doing...

Documentation Update

6

**Problem Faced** : While using the repo, it took some time to go through all the available augmentations and there examples as many markdowns don't have sample results, and many...

1. The _parse_batch() function throws a Key Error while trying to fetch x["PA"] . This is not consistent with torchxrayvision 2. The Kornia based data augmentation adds an additional dimension...

Training & Saving Model

1

Hi, Thanks for the paper & open sourcing the code. I was planning to use this approach to label a dataset and save the model. In future use the same...

Hi Team, As mentioned in the paper, will the code/data/weights be released ?