Jamesswiz

Where is conditional prior in CVAE?

1

I can see the implementation computes KL div between q(z|x,c) and p(z)=N(0,I) but the original formulation has conditional prior p(z|c). Can you explain why you are still using zero mean...

How to Generate WAV files with the detected segments

2

I am new to Pyhton I used the silence removal utility segments = aS.silenceRemoval(x, Fs, 0.020, 0.020, smoothWindow = 1.0, Weight = 0.3, plot = True) After getting the segments...

Out of memory issue on some GPUs

1

Hello Team, I ran the librespeech contextnet experiment with success on a RTX 3080 and V100 with a batch size of 4 and 8 respectively. However, the same setup gives...

Keras version compatibility: Obtain_Input_shape Error

1

### Tensorflow Version v1.11 Please replace this line with Tensorflow version you are using. ### Keras Version v2.2.4 Please replace this line with Keras version you are using. ### Keras-squeezenet...

Remove softmax classification layer and compute gradient

7

Hi, I want to remove the softmax layer and then compute gradients using guided backpropogation. I used pop() for this: model=load_model('nnet.h5', custom_objects={'keras':keras}) model.layers.pop() However, I am getting the following error...

Function definition not available

1

Hi ! I was testing your code but I am getting errors due to a undefined function. In tfrecords_model.py on line 342 there is a call to function _get_deduped_metrics_names(), however...

Filter visualization for sample-cnn

3

Hey! Thanks for sharing the implementation. I was wondering if you can also share the gradient accent filter visualization method, compatible with your keras implementation, or may be point me...

Replicating results from paper

1

Hi Team, This topic is quite new to me but interesting. I am interesting in replicating the TIMIT speech experiment. Can you please point out to a working example? Or...