alimeituan

hi,dear I see the kaggle dataset titanic, but the dataset is not you give, but as follows  so how to convert the data to your version  could you...

hi,dear directly run the [demo](https://github.com/aksnzhy/xlearn/blob/master/demo/classification/scikit_learn_demo/example_LR_iris.py), but see the **nan** , what's the matter? ``` [------------] Total time cost: 0.42 (sec) (array([[ nan, -1.63379 ], [ nan, -0.0229995], [ nan, 0.0296314],...

Only two model files in tacontron-20180906 ?

1

hi, a little strange that there are just two model files in tacontron-20180906/ , Could it be used in converting to tflite ? As we know, need the .meta file...

hi,dear I found that you get the features with postprocess, [here](https://github.com/devicehive/devicehive-audio-analysis/blob/master/audio/processor.py#L138) if I must postprocess ? thx

Could you please supply the trained model ?

1

Hi, See you again. How is everything going ? Could you please supply the trained model,I just want to have a test , emm,Could the model strip the silence ?...

hi,dear 大佬，1.14或者1.15的版本能用吗？

Dear, There is a question of the [script](https://github.com/MorvanZhou/Tensorflow-Tutorial/blob/master/tutorial-contents/301_simple_regression.py), Could it be a little hard,if the function is y=a*x^2 +b*x +c ? Any idea to change the code? Thx

how to use the data ?

10

Dear, Now I have the rnnoise_contributions.tar.gz and TSP48kall.zip , but where should I put them ? Need tar ? how to use ?

bug in dump_rnn.py

9

Hi, in the script, `f.write('const struct RNNModel rnnoise_model_{} = {{\n'.format(sys.argv[4]))` but in TRAINING `./dump_rnn.py weights.hdf5 ../src/rnn_data.c ../src/rnn_data.h` So where's the forth parameter ? and so the bug ups `Traceback (most...

how to understand the cost ?

2

Hi, As a new learner in deep learning, I'm a little puzzled about the cost definition, `def my_crossentropy(y_true, y_pred): return K.mean(2*K.abs(y_true-0.5) * K.binary_crossentropy(y_pred, y_true), axis=-1)` Could you please explain the...