s7ev3n

Weird problem on Jetson TX2

7

Hi, thanks for your implementation. I successfully trained a model on my own dataset, which has two classes. And I am deploying it on Jetson TX2. However, very weird things...

Paper on this code ?

1

Hi, Thanks for the great work, very interesting. I am wondering if you have written paper about this idea, since I did not find anthing when searching "Dense Lidar Net"....

Text tokenizer difference between foward and extract_feature

3

Hi, I notice that in `blip2_qformer.py`, in the `forward` function, the text_tokens are truncated to max_length which is 32, while in `extract_feature` function which to my understanding is an inference...

Hi, Thanks for your code. I am quite impressed by the pretty drawing of the network architecture. May I ask what tools you use? Thanks. -s7ev3n