Chang-Bin Zhang

Performance about TensorRT

6

I tried to accelerate my TensorFlow code by using TensorRT, but it didn't get any improvement? `in frozen_model, num of all_nodes = 893 in TensorRT_model, num of trt_engine_nodes = 0...

About the number of "utils.nValidElement"?

1

Hi @fangchangma , In your code, you regard the number of all pixels as "utils.nValidElement" when evaluation AbsRel and others, rather than the number of Lidar-point. Actually, I want to...

About performance of trained model.

5

Hi @zijundeng , I have loaded your pre-trained model and inference, but I got Ber = 5.20. I have ensured that my evaluation code is right, while I used your...

Ask for the training code

3

Hi, Is there the training code?

Install issue

7

Thanks for your time. I am installing detrex with developing mode, however, I encountered some issues. Here is my environment: torch=1.12.0_cuda11.3, CUDA11.3, GCC=5.4.0. I have installed detectron2 successfully, but there...

How can I train the model for road segmentation?

9

Hi, @jonahthelion and @Kevinpgalligan, how can I train the model for road segmentation?

Will you provide the training config file for ViT-L (66.0 AP)?

11

Thanks for your help.

Some running errors

2

- In ```train.py``` line 39, what is the package of ```import efficient_transformer```? This package is not used in the code. - After comment this line, a new exception is raised...

where is Uncertainty minimal query selection?

3

Thanks to the authors' work. I can not find the uncertainty minimal query selection module in the pytorch code. It uses a classification score to select tokens, as shown in...