hany
hany
@lyx326 Can you share steps you used for converting it to ONNX?
+1
> hello, @xinntao thanks for your work. I want to train GFPGANv1Clean, but neet to load related StyleGan2's pretrained model, I don't see a model for that? where can I...
> Hi @xinntao , Did you able to find the StyleGan2's pretrained model weights? Do you get the StyleGAN2's pretrained model now？Can you share it with me？
将build_lib.ps1中debug的编译注释掉，只保留在release下的编译，报错信息基本一样。 ### build_lib.ps1的更改如下： ##### Debug/Dynamic/MT #### #log "Debug/Dynamic/MT" #Remove-Item CMakeCache.txt -ErrorAction Ignore #Build "cmake -G Ninja $CMAKE_ARGS -DCMAKE_BUILD_TYPE=Debug -DMNN_WIN_RUNTIME_MT=ON .." #cp MNN.lib, MNN.dll, MNN.pdb $PACKAGE_LIB_PATH\Debug\Dynamic\MT #rm MNN.* ##### Debug/Dynamic/MD ####...
此问题还未解决，期待您的回复
@lshug Hi，thanks for your project！ I can do saved model → onnx successfully. But when I continue transfer onnx to openvino，there are some errors： `python mo_onnx.py --input_model E:\2D_Animation\first-order-model-tf-main\saved_models_float32\kp_detector.onnx --input img...
> @zhoumenghan There seems to be a bug in openvino model optimizer's GatherNdNormalizer.py. The line `if not all(np.take(indices, indices=[i], axis=-1) == 0):` should be `if not np.array(np.take(indices, indices=[i], axis=-1) ==...
+1!!!! I think ‘Total MAdd’ and 'Total Flops' results should exchange with each other.