saemundsson / semisupervised_vae Goto Github PK

Hello,

Trying to run the program, I face the following error:
I am using tensorflow v 0.12.0-rc1. before that when I was on version 0.11, I got another error as indicated here.

The message for the current error is:

WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/prettytensor/bookkeeper.py:258 in add_histogram_summary.: histogram_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30. Instructions for updating: Please switch to tf.summary.histogram. Note that tf.summary.histogram uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on their scope. WARNING:tensorflow:From /home/mdh/semisupervised_vae/vae.py:158 in train.: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02. Instructions for updating: Use tf.global_variables_initializerinstead. Traceback (most recent call last): File "train_vae.py", line 51, in <module> learning_rate = learning_rate, seed = seed, stop_iter = 30, print_every = 10, draw_img = 0 ) File "/home/mdh/semisupervised_vae/vae.py", line 206, in train self.saver.save( sess, self.save_path ) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1314, in save "Parent directory of {} doesn't exist, can't save.".format(save_path)) ValueError: Parent directory of checkpoints/model_VAE_0.0003-50_1481835936.26.cpkt doesn't exist, can't save.

I got very low accuracy using your model, and only get accurcy of 11.2% like a random guess. I'm curious of what's happening?

Hi, I've read your code about M1+M2 model, and there's a trick that removing the dimesions whose std less than min_std. And I was wondering if the reason was dimensions with std < min_std might not be informative to the model? Thanks.