Bang Vo

Hi @frgfm, so sorry about my posting, I'm still new to this repo and don't know where to post the question :( I'll post the reference to the code next...

HI @frgfm That is exactly what I need right now :D

I have the same issue, can't find out exactly where the GiT and ViT models are loaded. Can you please help me with this? @yashsandansing @alibaba-oss @Wangsherpa

Hi @ritutweets46, based on my current understanding, the path to change the ViT pre-trained model is in the [MyDetectionCheckpointer](https://github.com/AlibabaResearch/AdvancedLiterateMachinery/blob/e1e42feec21c1af0ab4f8c7e69f3089c912c0c25/DocumentUnderstanding/VGT/object_detection/ditod/VGTcheckpointer.py#L195) class within [VGTcheckpointer.py](https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/VGT/object_detection/ditod/VGTcheckpointer.py) ```python class MyDetectionCheckpointer(DetectionCheckpointer): def _load_model(self, checkpoint: Any) ->...

> Hi, before executing the functin, `Lazy load` the plugin. > > This is my resulting lazy configuration, that uses npx is available: > > ``` > { > --...

I have read the CLA Document and I sign the CLA

Can you do a quick check on this @glenn-jocher?

Many thanks for your help @glenn-jocher I'll recheck the code for any new issues while you prepare for your next action.

I have tried your solution but the image still doesn't show in the terminal. Your fix did get the correct node, but it seems like the wezterm doesn't show image...