diff options
| author |  Andrew Harp <andrewharp@google.com> | 2017-03-01 17:59:22 -0800 |
|---|---|---|
| committer |  TensorFlower Gardener <gardener@tensorflow.org> | 2017-03-01 18:08:24 -0800 |
| commit | 3e975ea978bac4d861bb09328b06f3c316212611 (patch) | |
| tree | 79bac044c9723df8443495eb962c2dd98a2ed421 /tensorflow/examples/learn | |
| parent | 8043a27ed77f59bb68409070f2bfa01df0e04b89 (diff) | |
Merge changes from github.
Change: 148954491
Diffstat (limited to 'tensorflow/examples/learn')
| -rw-r--r-- | tensorflow/examples/learn/mnist.py | 4 | ||||
| -rw-r--r-- | tensorflow/examples/learn/text_classification.py | 9 |
2 files changed, 9 insertions, 4 deletions
diff --git a/tensorflow/examples/learn/mnist.py b/tensorflow/examples/learn/mnist.py index 6e5fe7891b..15cf4b91dd 100644 --- a/tensorflow/examples/learn/mnist.py +++ b/tensorflow/examples/learn/mnist.py @@ -46,13 +46,13 @@ def conv_model(feature, target, mode): # First conv layer will compute 32 features for each 5x5 patch with tf.variable_scope('conv_layer1'): - h_conv1 = layers.convolution( + h_conv1 = layers.convolution2d( feature, 32, kernel_size=[5, 5], activation_fn=tf.nn.relu) h_pool1 = max_pool_2x2(h_conv1) # Second conv layer will compute 64 features for each 5x5 patch. with tf.variable_scope('conv_layer2'): - h_conv2 = layers.convolution( + h_conv2 = layers.convolution2d( h_pool1, 64, kernel_size=[5, 5], activation_fn=tf.nn.relu) h_pool2 = max_pool_2x2(h_conv2) # reshape tensor into a batch of vectors diff --git a/tensorflow/examples/learn/text_classification.py b/tensorflow/examples/learn/text_classification.py index a3a5f9e3e9..c3d00a11b9 100644 --- a/tensorflow/examples/learn/text_classification.py +++ b/tensorflow/examples/learn/text_classification.py @@ -104,8 +104,13 @@ def main(unused_argv): # Process vocabulary vocab_processor = learn.preprocessing.VocabularyProcessor(MAX_DOCUMENT_LENGTH) - x_train = np.array(list(vocab_processor.fit_transform(x_train))) - x_test = np.array(list(vocab_processor.transform(x_test))) + + x_transform_train = vocab_processor.fit_transform(x_train) + x_transform_test = vocab_processor.transform(x_test) + + x_train = np.array(list(x_transform_train)) + x_test = np.array(list(x_transform_test)) + n_words = len(vocab_processor.vocabulary_) print('Total words: %d' % n_words) |