Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: keras-team/keras
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master
Choose a base ref
...
head repository: elfscript/keras
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: master
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 15 commits
  • 19 files changed
  • 1 contributor

Commits on Sep 27, 2016

  1. try addition_rnn.py

    @3hdeng
    3hdeng committed Sep 27, 2016
    Configuration menu
    Copy the full SHA
    8e64e44 View commit details
    Browse the repository at this point in the history

Commits on Sep 29, 2016

  1. reading note: addition_rnn.txt

    @3hdeng
    3hdeng committed Sep 29, 2016
    Configuration menu
    Copy the full SHA
    854f7ff View commit details
    Browse the repository at this point in the history

  2. myreadme.txt , keras/keras/

    @3hdeng
    3hdeng committed Sep 29, 2016
    Configuration menu
    Copy the full SHA
    1a8f76d View commit details
    Browse the repository at this point in the history

  3. read keras/engine/training.py, Model(), model.fit(), standardize_inpu… 

    …t_data()
    @3hdeng
    3hdeng committed Sep 29, 2016
    Configuration menu
    Copy the full SHA
    1d2e53b View commit details
    Browse the repository at this point in the history

  4. one-hot vector, batch_size and lstm_size(output_dim)

    @3hdeng
    3hdeng committed Sep 29, 2016
    Configuration menu
    Copy the full SHA
    d2774a8 View commit details
    Browse the repository at this point in the history

Commits on Oct 3, 2016

  1. K.function([model.layers[0].input],

    @3hdeng
    3hdeng committed Oct 3, 2016
    Configuration menu
    Copy the full SHA
    6446567 View commit details
    Browse the repository at this point in the history

  2. K.function() has to be defined after model.fit() to get the updated(t… 

    …rained) response, otherwise the results seem to be the one from the initial random weightings
    @3hdeng
    3hdeng committed Oct 3, 2016
    Configuration menu
    Copy the full SHA
    9902f17 View commit details
    Browse the repository at this point in the history

  3. cleaner version to try addition_rnn

    @3hdeng
    3hdeng committed Oct 3, 2016
    Configuration menu
    Copy the full SHA
    f1ff93e View commit details
    Browse the repository at this point in the history

Commits on Oct 8, 2016

  1. has problem to get output from K.function(), must feed a value for pl… 

    …aceholder tensor 'keras_learning_phase' with dtype uint8?
    @3hdeng
    3hdeng committed Oct 8, 2016
    Configuration menu
    Copy the full SHA
    d8e4dc7 View commit details
    Browse the repository at this point in the history

Commits on Oct 10, 2016

  1. mnist_mlp.py, TensorBoard, why no error/no histogram

    @3hdeng
    3hdeng committed Oct 10, 2016
    Configuration menu
    Copy the full SHA
    8271ade View commit details
    Browse the repository at this point in the history

  2. Merge branch 'master' of https://github.com/fchollet/keras

    @3hdeng
    3hdeng committed Oct 10, 2016
    Configuration menu
    Copy the full SHA
    3dd2e8e View commit details
    Browse the repository at this point in the history

  3. how to feed learning_phase to K.function()

    @3hdeng
    3hdeng committed Oct 10, 2016
    Configuration menu
    Copy the full SHA
    9256ef3 View commit details
    Browse the repository at this point in the history

Commits on Oct 14, 2016

  1. imdb-cnn/lstm/fasttext

    @3hdeng
    3hdeng committed Oct 14, 2016
    Configuration menu
    Copy the full SHA
    4f7aeeb View commit details
    Browse the repository at this point in the history

  2. imdb_lstm seems the slowest training,but no gain on accuracy

    @3hdeng
    3hdeng committed Oct 14, 2016
    Configuration menu
    Copy the full SHA
    ee1092f View commit details
    Browse the repository at this point in the history

Commits on Oct 20, 2016

  1. add a jpg image to try deep_dream.py

    @3hdeng
    3hdeng committed Oct 20, 2016
    Configuration menu
    Copy the full SHA
    96f878f View commit details
    Browse the repository at this point in the history
Loading