fmbao issues

Results 11 issues of


                                            fmbao

can't convert same onnx by provided python file.

I convert onnx file by convert_weights_to_onnx.py. The onnx files converted is not sames onnx files provided

inference question

为什么我训练完模型之后,然后推理出来的音频都是嘟嘟的声音,我开始以为是用于推理的音频的问题,我直接拿训练的音频进行推理还是嘟嘟的声音,这是为啥呢

test_fft() in ConvSTFT.py can't calculate correctly

It throw the error that: operands could not be broadcast together with shapes (514,399) (257,397)

ModuleNotFoundError: No module named 'libpymo'

Try any method,but throw the error: `Traceback (most recent call last): File "deepspeech2_quanteval.py", line 36, in from aimet_common.defs import QuantScheme File "/usr/local/lib/python3.6/dist-packages/aimet_common/defs.py", line 46, in import libpymo ModuleNotFoundError: No module...

I try to quantize deepspeech demo,but error happend

`ImportError: /home/mi/anaconda3/envs/aimet/lib/python3.7/site-packages/aimet_common/x86_64-linux-gnu/aimet_tensor_quantizer-0.0.0-py3.7-linux-x86_64.egg/AimetTensorQuantizer.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZNK2at6Tensor8data_ptrIfEEPT_v` platform:Ubuntu 18.04 GPU: nvidia 2070 CUDA:11.1 pytorch python:3.7

ImportError: /usr/local/lib/python3.6/dist-packages/aimet_common/x86_64-linux-gnu/aimet_tensor_quantizer-0.0.0-py3.6-linux-x86_64.egg/AimetTensorQuantizer.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZNK2at6Tenso

when I run `deepspeech2_quanteval.py` ,the Error throw `ImportError: /usr/local/lib/python3.6/dist-packages/aimet_common/x86_64-linux-gnu/aimet_tensor_quantizer-0.0.0-py3.6-linux-x86_64.egg/AimetTensorQuantizer.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZNK2at6Tenso`

发生了一个错误

博主，你好，你的代码很棒。但是我在运行你的代码时发生了一个错误： `Traceback (most recent call last): File "G:\desktop\myProject\WGAN_gp\gan_mnist.py", line 253, in generate_image(iteration, netG) File "G:\desktop\myProject\WGAN_gp\gan_mnist.py", line 119, in generate_image 'tmp/mnist/samples_{}.png'.format(frame) File "G:\desktop\myProject\WGAN_gp\tflib\save_images.py", line 36, in save_images img[j*h:j*h+h, i*w:i*w+w] = x...

How to generate the test frame.txt & How to use image to synthesize as video

I'm so confused about how to generate the test frame.txt. And how to use the image to generate video.

Generate pb file command is error

correct is ```python python freeze.py --num_classes 12 --checkpoint_path work/v1/TCResNet8Model-1.0/mfcc_40_3010_0.001_mom_l1/TCResNet8Model-30000 --output_name softmax --preprocess_method no_preprocessing --height 49 --width 40 --channels 1 TCResNet8Model --width_multiplier 1.0 ```