Bruno Nascimento
Bruno Nascimento
> Here are the steps I did, but ended up failing anyway. > > ## Step 1: fix UINT8 error > Here is a script that generates a new frozen...
Hi @douglasrizzo , I've been looking into this issue and it seems that tensorRT has this operation under its plugins. See https://github.com/NVIDIA/TensorRT/tree/master/plugin/batchedNMSPlugin or https://github.com/NVIDIA/TensorRT/tree/master/plugin/nmsPlugin The reason might be because they...
was able to solve it with --hparam_str="num_classes=278"
Thanks @ljn917 @serizba I stumbled into this thread, after failing alot to use c/cc tensorflow 2.x APIs. Your work here gave me lots of good insights. Please keep it up
A fix for that can be found here: http://theperfectmixture.wordpress.com/2012/03/28/clahe-in-opencv-removing-the-seg-fault/
We face this issue as well: just open pylonviewer on a jetson orin I randomly get the following `[2023-02-28 16:08:13.856][Info] Basler acA1920-40gc (24553637): "Basler acA1920-40gc (24553637)" has been removed. [2023-02-28...
I can also confirm that cpp results are wrong
see the answer here: https://github.com/ultralytics/ultralytics/issues/7657#issuecomment-1940475053
K_s didn't help much, I still get fragmented clusters with just 2 images. Tested ranges from 5 to 100
> It can be changed to "w = (1 - (np.exp(**N_b[0]**)/np.sum(np.exp(N_b))))" because the N_b is sorted by k. In the other hand, I want to figure out some explanation of...