Top Questions

1. Float16 is much slower than Float32 and Float64 in numpy
   10 votes

   2 answers
2. Handling zero multiplied with NaN
   6 votes

   3 answers
3. InaccessibleTensorError - When using `tf.keras.layers.Layer` output in loop condition of another layer
   2 votes

   1 answers
4. Keras LSTM - looping over variable sequence length
   1 votes

   1 answers