Yewen Zhou

ABINet deployment

2

Thanks for the response here https://github.com/open-mmlab/mmocr/issues/1124 1. just to confirm, ABINet is currently not supported to be converted to tensorRT using MMDeploy, right? 2. if possible, could you point out...

### Issue If you click the link on the github page https://github.com/NVIDIA-AI-IOT/torch2trt  It would have 404 Error

I am trying to convert a MMOCR recognition model ABINet to tensorRT. As the syntax implies we need to do something like this ``` # create example data x =...

Confused about Cumulative Inference Duration vs. PredictionTime

3

### 📚 The doc issue I am running a model on TorchServe and I am trying to see how long it takes for inference. If I use logging and view...

Does TorchServe have better performance than calling Pytorch

4

From doc here: https://github.com/pytorch/serve It says TorchServe is a tool used to serve Pytorch models in production. **I am wondering, in theory, if we can expect to have a better...

TorchServe How to Curl Multiple Images Properly

8

I am using TorchServe to potentially serve a model from MMOCR (https://github.com/open-mmlab/mmocr), and I have several questions: 1. I tried to do inference on hundreds of images together using batch...

Output doesn't make sense

1

I tested this image  (To mimic the blurred/mosaic behavior of the CORD dataset, I cropped the header and this is the resulting image) Here is the code I used...

I noticed that the CORD data used in fine-tuning here: https://drive.google.com/drive/folders/17ZK7OulhAg0Lz9w4lT19kXKX9zeeDjAw are blurred on the top (prob due to privacy concerns). I am just wondering are those blurred before fine-tuning...

I read the paper and some other posts and still feel confused about how to use prompts 1. what are some available prompts? for example, I see there are ""...

## Issue When using Synthdog to generate some data, I noticed when the character is backslash, the image would not be able to render it properly. Instead, it would render...