adventures-in-ml-code

adventures-in-ml-code copied to clipboard

I ran your example in Colab. Here is the gist: https://gist.github.com/gosha1128/38cbb8dd1aaf8ca229d4760880e13634 The results aren't the same as yours. Any thoughts?

sourcesync

I think they moved gfile.GFile into tf.io package in tf2.0 hence using tf.gfile.GFile is throwing error.

ksrath0re

When `l == 1`, `h[l] == x` There's no need for the `if` statement

jaygood

Changes that makes possible to train model with latest PyTorch version

solesensei

replace keras.layer.merge by keras.layer.dot to generate similarity layer.

yzhou1122

Keras word2vec is much more faster than tensorflow word2vec ?

1

Thanks for your work. I had a question about word2vec. I ran both of your codes of word2vec viz Keras_word2vec.py and tf_word2vec.py !! Keras word2vec with Tensorflow backend seems faster...

muthiyanbhushan

keras_lstm.py does not show the results claimed in the tutorial?

2

I run python keras_lstm.py 1 with: detlef@ubuntu-i7:~$ python -c 'import tensorflow as tf; print(tf.__version__)' # for Python 2 1.12.0 (tested it with turned off gpu too but use cuda 9.1...

dsmic

keras_word2vec.py doesn't converge

2

Hi, please see below - it doesn't converge...can you confirm it is still working on your side? fyi - running on python 2.7, keras 2.1.4, TensorFlow 1.5 Iteration 75600, loss=0.764099955559...

romeokienzler

Two things. This tutorial uses `softmax_cross_entropy_with_logits()` instead of `softmax_cross_entropy_with_logits_v2().` That should be changed. Also, this is importing the MNIST database from a soon-to-be-outdated source. I got it working by replacing...

spencerkraisler

Merge Module is Depreciated

2

https://github.com/adventuresinML/adventures-in-ml-code/blob/6e6811a9aee695c40176953000c29b54741e741f/keras_word2vec.py#L98

Xeonen