lawo123

cudaGetDevice() failed. Status: CUDA driver version is insufficient for CUDA runtime version

2

I used onnx2keras tag v0.0.5, tensorflow-gpu 1.14.0 cuda 10.0.when i run ,i got the error 'tensorflow.python.framework.errors_impl.InternalError: cudaGetDevice() failed. Status: CUDA driver version is insufficient for CUDA runtime version'.If i used...

I used onnx2keras tag v0.0.5, tensorflow-gpu 1.14.0 cuda 10.0.when i run ,i got the error 'tensorflow.python.framework.errors_impl.InternalError: cudaGetDevice() failed. Status: CUDA driver version is insufficient for CUDA runtime version'.If i used...

**Describe the bug** how to set opset_version=11? `torch.onnx.export(model, dummy_input, "test.onnx", verbose=True, opset_version=11)` @tehsenaus

Can I use infrared images as input?

6

Can I use infrared images as input? @liguohao96

build OpenCV for T-head's Xuantie-906 CPU as riscv64-071-gcc.toolchain.cmake,error illegal instruction

3

##### System information (version) - OpenCV =>4.5.3 - Operating System / Platform => T-head's Xuantie-906 CPU - Compiler =>risc-v ##### Detailed description I build OpenCV for T-head's Xuantie-906 CPU,follow https://github.com/opencv/opencv/wiki/OpenCV-RISC-V....

直接训练coco数据集只达到了mAp 0.69

12

 您好，按照您的代码训练fastpose在coco数据集上的结果，##### Epoch 199 | gt mAP: 0.7252916811102725 | rcnn mAP: 0.6978454378890657 #####，没有复现出您mAP 0.72的结果呢 @Fang-Haoshu

Longer Chinese sentences use fastspeech2 to synthesize exceptions

4

Longer Chinese sentences use fastspeech2 to synthesize exceptions. TEXT:在一个拥有 2500 万人口的不发达且以孤立着称的国家，绝大多数人被认为没有接种疫苗，它有可能成为一场规模巨大的人道主义灾难，威胁到几乎任何政府的权力控制 在世界上。 WAVE：[2.zip](https://github.com/TensorSpeech/TensorFlowTTS/files/9138051/2.zip) @dathudeptrai

As shown in the figure below, the inference speed of tflite is much slower than that of tensorflow.Why? 

为什么你们的fastspeech2的长文本中文合成效果好？

3

同样用baker数据集训练 我训练的结果 长文本后半段就异常了 [our_fastspeech2.zip](https://github.com/PaddlePaddle/PaddleSpeech/files/9205043/our_fastspeech2.zip) 你们的fastspeech2预训练模型的结果就是正常的，为什么你们支持的长度比我的长，而数据集是一致的 [paddle_fastspeech2.zip](https://github.com/PaddlePaddle/PaddleSpeech/files/9205044/paddle_fastspeech2.zip)