About issus

Hello everyone,i want to consult a question。When I use rnnoise to denoise, I use the same model structure, but the noise denoise effect is very different from the official demo....

About memory of rnn-denoise

1

Hello! I would like to ask about how much memory space rnn-denoise needs when it is deployed to the chip for denoise.

Can anyone share weight and model files?I also have sent a emial to the author yesterday, but he haven't replied yet. my email is [email protected]

How to use tensorflow to conv_stft?

1

Hi,I use tensorflow to conv_stft like this: def init_kernels(win_len, win_inc, fft_len, win_type=None, invers=False): if win_type == 'None' or win_type is None: window = np.ones(win_len) else: window = get_window(win_type, win_len, fftbins=True)**0.5...

Tflite

1

Hi, when i want to run example.cc have some issus: FAILED: libmylib.dll libmylib.dll.a

Click to expand! ### Issue Type Bug ### Have you reproduced the bug with TF nightly? Yes ### Source source ### Tensorflow Version tf 2.X ### Custom Code Yes ###...

libncnn.a库文件在编译器上的链接错误

3

## error log | 日志或报错信息 | ログ 编译出来c_api的库文件后，在链接编译时大量报错： (allocator.cpp:28: undefined reference to `operator delete(void*, unsigned int)') allocator.cpp:42: undefined reference to `operator new(unsigned int)' c_api.cpp:888: undefined reference to `operator new(unsigned int)'...

DequantizeLinear and QuantizeLinear

1

## expectation | 诉求 | 期待する 因为并没有用到复杂的算子，所以尝试将int8量化后的tflite转换成onnx，再将onnx转换成ncnn时，会出现“QuantizeLinear not supported yet!DequantizeLinear not supported yet!”，onnxz中的这两个在ncnn中并不支持，不知道能否用其他方法解决？

使用riscv工具链编译时的一个问题

3

## detail | 详细描述 | 詳細な説明 我在使用riscv工具链编译ncnn的时候出现一个错误： [ 99%] Built target ncnn [ 99%] Building CXX object benchmark/CMakeFiles/benchncnn.dir/benchncnn.cpp.obj [100%] Linking CXX executable benchncnn /home/Xuantie-900-gcc-elf-newlib-x86_64-V2.0.5/bin/../lib/gcc/riscv64-unknown-elf/10.2.0/../../../../riscv64-unknown-elf/bin/ld: cannot find -lpthread collect2: error: ld...

## expectation | 诉求 | 期待する 我想请问下，假如我的模型是处理语音数据的，输入是经过FFT处理后的数据，那么怎么通过ncnn的量化工具“ncnn2int8”进行量化，是否有例子可以参考？谢谢。我是想将tf模型转ncnn后再用ncnn进行量化。