Hongbin Lin

I find difference between local loss in the download logs (about 3.05 in cifar10) and best result (3.35 in cifar10) in your paper , can anyone explain the diffenence between...

Hello, Thank you for your awesome work! Could you please release compression result test on VTL and UVG datasets, like PSNR(MS-SSIM) vs. bit per pixel? It'd be great if you...

run diffusion demo error

7

1. MNN版本：2.9.3 2. 编译与运行参考 https://mnn-docs.readthedocs.io/en/latest/transformers/diffusion.html 3. 编译MNN和MNN转换工具 cmake .. -DMNN_BUILD_DIFFUSION=ON -DMNN_BUILD_OPENCV=ON -DMNN_IMGCODECS=ON -DMNN_OPENCL=ON -DMNN_SEP_BUILD=OFF -DMNN_SUPPORT_TRANSFORMER_FUSE=ON -DMNN_BUILD_CONVERTER=ON -DMNN_BUILD_TORCH=ON 4. diffusion模型torch转onnx cd mnn_path/transformers/diffusion/ python export/onnx_export.py \ --model_path "IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1" \ --output_path onnx_save_path 5....

Unable to initialize class AimetTensorQuantizer: Cannot import AimetTensorQuantizer. Please build AimetTensorQuantizer and add artifact path to PYTHONPATH to resolve this issue

4

aimet-torch=1.32.2, torch=2.2.2