wentao

Results 26 issues of wentao

Hi,I find that you have successfully trained to complete the thundernet model based on voc2007. About the dataset, I want to know how do I prepare it ? train_path =...

There is a comparison of speed analysis before and after int8 quantization ?

Is there any demo provided for the cuda accelerated conversion example of yuv420sp to bgr? thanks!

feature request

Excuse me, if I need to deploy llama2 on Qualcomm Snapdragon chip through ExecuTorch and want to use NPU computing power as an inference computing unit, what do I need...

need-user-input
partner: qualcomm
triaged

I would like to ask if nvcv::Tensor currently supports dimension splicing. For example, when I perform batch preprocessing here, different frame images will produce multiple nvcv::Tensor: nvcv::Tensor inputTensor1(2, {m_model_width, m_model_height},...

feature request

### Describe the feature Are there any plans to support accelerated training of the StableDiffusion3 algorithm model?

enhancement