Qia98

"This version of TensorRT does not support dynamic axes." failure of TensorRT 8.5.2 and 8.6.1 when running groundingdino.onnx on GPU Tesla V100 and Tesla T4

9

## Description I tried to convert grouding.onnx to tensorrt on GPU, but it fails with the error below torch2onnx commend: ``` caption = "the running dog ." #". ".join(input_text) input_ids...

Retraining 512x512 with 68 keypoints，then retraining 512x512 with dlib 68 keypoints detector

2

I want to retrain FOMM with 68 keypoints (512x512) and release it publicly, if successful. In addition, I prefer to retrain fomm based on dlib 68 keypoints detector. This allows...

train 512 or higher resolution

5

I'm going to train a 512x512 face model and release it to the public under the public domain. But I met some challenge in getting 512 datasets. I have eight...

Calculate the parameters and FLOPs

2

How to calculate the parameters and FLOPs of this model?

I would like to use MiniGPTv2 for image classification tasks, and the idea is to calculate the ITM (Image-Text Matching) score between the image and category text. Could you please...

freeze most of the layers and train head

1

I would like to train on a custom dataset, but I want to freeze most of the layers and only train the last few layers (like head or decoder). I...

基于图像提示的开集目标检测模型

1

GroundingDINO是一个非常棒的基于文本提示的开集目标检测工作，你们有想法探究一下基于图像提示的开集目标检测模型吗？ 目前[MQ-Det](https://github.com/YifanXu74/MQ-Det)是一个更接近的工作，他们采用文本提示 + 图像提示来做目标检测。