notebook.community

Edit and run

Build Experiment from TF Estimator

Embeds a 3 layer FCN model to predict MNIST handwritten digits in a Tensorflow Experiment. FCN model is built using the Estimator DNNClassifier from the tf.contrib.learn package.





In [1]:



    


from __future__ import division, print_function
import matplotlib.pyplot as plt
import numpy as np
import os
import shutil
import tensorflow as tf



    











In [2]:



    


DATA_DIR = "../../data"
TRAIN_FILE = os.path.join(DATA_DIR, "mnist_train.csv")
TEST_FILE = os.path.join(DATA_DIR, "mnist_test.csv")

MODEL_DIR = os.path.join(DATA_DIR, "expt-tf-model")

NUM_FEATURES = 784
NUM_CLASSES = 10
NUM_STEPS = 100

Prepare Data





In [3]:



    


def parse_file(filename):
    xdata, ydata = [], []
    fin = open(filename, "rb")
    i = 0
    for line in fin:
        if i % 10000 == 0:
            print("{:s}: {:d} lines read".format(
                os.path.basename(filename), i))
        cols = line.strip().split(",")
        ydata.append(int(cols[0]))
        xdata.append([float(x) / 255. for x in cols[1:]])
        i += 1
    fin.close()
    print("{:s}: {:d} lines read".format(os.path.basename(filename), i))
    y = np.array(ydata)
    X = np.array(xdata)
    return X, y

Xtrain, ytrain = parse_file(TRAIN_FILE)
Xtest, ytest = parse_file(TEST_FILE)
print(Xtrain.shape, ytrain.shape, Xtest.shape, ytest.shape)



    


















    






mnist_train.csv: 0 lines read
mnist_train.csv: 10000 lines read
mnist_train.csv: 20000 lines read
mnist_train.csv: 30000 lines read
mnist_train.csv: 40000 lines read
mnist_train.csv: 50000 lines read
mnist_train.csv: 60000 lines read
mnist_test.csv: 0 lines read
mnist_test.csv: 10000 lines read
(60000, 784) (60000,) (10000, 784) (10000,)

















In [4]:



    


# these functions are parameters to the classifier
def train_input_fn():
    return tf.constant(Xtrain), tf.constant(ytrain)

def test_input_fn():
    return tf.constant(Xtest), tf.constant(ytest)

Define Estimator

The tf.contrib.learn package provides several Estimators out of the box.

* tf.contrib.learn.LinearRegressor
* tf.contrib.learn.LinearClassifier
* tf.contrib.learn.DNNRegressor
* tf.contrib.learn.DNNClassifier




In [5]:



    


shutil.rmtree(MODEL_DIR, ignore_errors=True)
feature_cols = [tf.contrib.layers.real_valued_column("", 
    dimension=NUM_FEATURES)]
estimator = tf.contrib.learn.DNNClassifier(feature_columns=feature_cols,
    hidden_units=[512, 256], n_classes=NUM_CLASSES,
    model_dir=MODEL_DIR)



    


















    






INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_save_checkpoints_secs': 600, '_num_ps_replicas': 0, '_keep_checkpoint_max': 5, '_task_type': None, '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x135d23d10>, '_model_dir': '../../data/expt-tf-model', '_save_checkpoints_steps': None, '_keep_checkpoint_every_n_hours': 10000, '_session_config': None, '_tf_random_seed': None, '_environment': 'local', '_num_worker_replicas': 0, '_task_id': 0, '_save_summary_steps': 100, '_tf_config': gpu_options {
  per_process_gpu_memory_fraction: 1
}
, '_evaluation_master': '', '_master': ''}

Train Estimator





In [6]:



    


estimator.fit(input_fn=train_input_fn, steps=NUM_STEPS)



    


















    






WARNING:tensorflow:From /Users/palsujit/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:625: scalar_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.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Saving checkpoints for 1 into ../../data/expt-tf-model/model.ckpt.
INFO:tensorflow:loss = 2.33514, step = 1
INFO:tensorflow:Saving checkpoints for 100 into ../../data/expt-tf-model/model.ckpt.
INFO:tensorflow:Loss for final step: 0.320789.










    
Out[6]:








DNNClassifier(params={'head': <tensorflow.contrib.learn.python.learn.estimators.head._MultiClassHead object at 0x107d0b590>, 'hidden_units': [512, 256], 'feature_columns': (_RealValuedColumn(column_name='', dimension=784, default_value=None, dtype=tf.float32, normalizer=None),), 'embedding_lr_multipliers': None, 'optimizer': None, 'dropout': None, 'gradient_clip_norm': None, 'activation_fn': <function relu at 0x11061ff50>, 'input_layer_min_slice_size': None})

Evaluate Estimator





In [7]:



    


accuracy_score = estimator.evaluate(input_fn=test_input_fn,
                                    steps=1)["accuracy"]
print("accuracy: {:.3f}".format(accuracy_score))



    


















    






WARNING:tensorflow:From /Users/palsujit/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:625: scalar_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.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
INFO:tensorflow:Starting evaluation at 2017-05-31-00:24:40
INFO:tensorflow:Restoring parameters from ../../data/expt-tf-model/model.ckpt-100
INFO:tensorflow:Evaluation [1/1]
INFO:tensorflow:Finished evaluation at 2017-05-31-00:24:41
INFO:tensorflow:Saving dict for global step 100: accuracy = 0.917, global_step = 100, loss = 0.305549
accuracy: 0.917

alternatively...

Define Experiment

A model is wrapped in an Estimator, which is then wrapped in an Experiment. Once you have an Experiment, you can run this in a distributed manner on CPU, GPU or TPU.





In [8]:



    


def experiment_fn(run_config, params):
    feature_cols = [tf.contrib.layers.real_valued_column("",
        dimension=NUM_FEATURES)]
    estimator = tf.contrib.learn.DNNClassifier(
        feature_columns=feature_cols,
        hidden_units=[512, 256],
        n_classes=NUM_CLASSES,
        config=run_config)
    return tf.contrib.learn.Experiment(
        estimator=estimator,
        train_input_fn=train_input_fn,
        train_steps=NUM_STEPS,
        eval_input_fn=test_input_fn)

Run Experiment





In [9]:



    


shutil.rmtree(MODEL_DIR, ignore_errors=True)
tf.contrib.learn.learn_runner.run(experiment_fn, 
    run_config=tf.contrib.learn.RunConfig(
        model_dir=MODEL_DIR))



    


















    






WARNING:tensorflow:uid (from tensorflow.contrib.learn.python.learn.estimators.run_config) is experimental and may change or be removed at any time, and without warning.
INFO:tensorflow:Using config: {'_model_dir': '../../data/expt-tf-model', '_save_checkpoints_secs': 600, '_num_ps_replicas': 0, '_keep_checkpoint_max': 5, '_tf_random_seed': None, '_task_type': None, '_environment': 'local', '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x117f7ed50>, '_tf_config': gpu_options {
  per_process_gpu_memory_fraction: 1
}
, '_num_worker_replicas': 0, '_task_id': 0, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_evaluation_master': '', '_keep_checkpoint_every_n_hours': 10000, '_master': '', '_session_config': None}
WARNING:tensorflow:uid (from tensorflow.contrib.learn.python.learn.estimators.run_config) is experimental and may change or be removed at any time, and without warning.
WARNING:tensorflow:From /Users/palsujit/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py:268: __init__ (from tensorflow.contrib.learn.python.learn.monitors) is deprecated and will be removed after 2016-12-05.
Instructions for updating:
Monitors are deprecated. Please use tf.train.SessionRunHook.
WARNING:tensorflow:From /Users/palsujit/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:625: scalar_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.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Saving checkpoints for 1 into ../../data/expt-tf-model/model.ckpt.
INFO:tensorflow:loss = 2.3162, step = 1
WARNING:tensorflow:From /Users/palsujit/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:625: scalar_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.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
INFO:tensorflow:Starting evaluation at 2017-05-31-00:25:45
INFO:tensorflow:Restoring parameters from ../../data/expt-tf-model/model.ckpt-1
INFO:tensorflow:Evaluation [1/100]
INFO:tensorflow:Evaluation [2/100]
INFO:tensorflow:Evaluation [3/100]
INFO:tensorflow:Evaluation [4/100]
INFO:tensorflow:Evaluation [5/100]
INFO:tensorflow:Evaluation [6/100]
INFO:tensorflow:Evaluation [7/100]
INFO:tensorflow:Evaluation [8/100]
INFO:tensorflow:Evaluation [9/100]
INFO:tensorflow:Evaluation [10/100]
INFO:tensorflow:Evaluation [11/100]
INFO:tensorflow:Evaluation [12/100]
INFO:tensorflow:Evaluation [13/100]
INFO:tensorflow:Evaluation [14/100]
INFO:tensorflow:Evaluation [15/100]
INFO:tensorflow:Evaluation [16/100]
INFO:tensorflow:Evaluation [17/100]
INFO:tensorflow:Evaluation [18/100]
INFO:tensorflow:Evaluation [19/100]
INFO:tensorflow:Evaluation [20/100]
INFO:tensorflow:Evaluation [21/100]
INFO:tensorflow:Evaluation [22/100]
INFO:tensorflow:Evaluation [23/100]
INFO:tensorflow:Evaluation [24/100]
INFO:tensorflow:Evaluation [25/100]
INFO:tensorflow:Evaluation [26/100]
INFO:tensorflow:Evaluation [27/100]
INFO:tensorflow:Evaluation [28/100]
INFO:tensorflow:Evaluation [29/100]
INFO:tensorflow:Evaluation [30/100]
INFO:tensorflow:Evaluation [31/100]
INFO:tensorflow:Evaluation [32/100]
INFO:tensorflow:Evaluation [33/100]
INFO:tensorflow:Evaluation [34/100]
INFO:tensorflow:Evaluation [35/100]
INFO:tensorflow:Evaluation [36/100]
INFO:tensorflow:Evaluation [37/100]
INFO:tensorflow:Evaluation [38/100]
INFO:tensorflow:Evaluation [39/100]
INFO:tensorflow:Evaluation [40/100]
INFO:tensorflow:Evaluation [41/100]
INFO:tensorflow:Evaluation [42/100]
INFO:tensorflow:Evaluation [43/100]
INFO:tensorflow:Evaluation [44/100]
INFO:tensorflow:Evaluation [45/100]
INFO:tensorflow:Evaluation [46/100]
INFO:tensorflow:Evaluation [47/100]
INFO:tensorflow:Evaluation [48/100]
INFO:tensorflow:Evaluation [49/100]
INFO:tensorflow:Evaluation [50/100]
INFO:tensorflow:Evaluation [51/100]
INFO:tensorflow:Evaluation [52/100]
INFO:tensorflow:Evaluation [53/100]
INFO:tensorflow:Evaluation [54/100]
INFO:tensorflow:Evaluation [55/100]
INFO:tensorflow:Evaluation [56/100]
INFO:tensorflow:Evaluation [57/100]
INFO:tensorflow:Evaluation [58/100]
INFO:tensorflow:Evaluation [59/100]
INFO:tensorflow:Evaluation [60/100]
INFO:tensorflow:Evaluation [61/100]
INFO:tensorflow:Evaluation [62/100]
INFO:tensorflow:Evaluation [63/100]
INFO:tensorflow:Evaluation [64/100]
INFO:tensorflow:Evaluation [65/100]
INFO:tensorflow:Evaluation [66/100]
INFO:tensorflow:Evaluation [67/100]
INFO:tensorflow:Evaluation [68/100]
INFO:tensorflow:Evaluation [69/100]
INFO:tensorflow:Evaluation [70/100]
INFO:tensorflow:Evaluation [71/100]
INFO:tensorflow:Evaluation [72/100]
INFO:tensorflow:Evaluation [73/100]
INFO:tensorflow:Evaluation [74/100]
INFO:tensorflow:Evaluation [75/100]
INFO:tensorflow:Evaluation [76/100]
INFO:tensorflow:Evaluation [77/100]
INFO:tensorflow:Evaluation [78/100]
INFO:tensorflow:Evaluation [79/100]
INFO:tensorflow:Evaluation [80/100]
INFO:tensorflow:Evaluation [81/100]
INFO:tensorflow:Evaluation [82/100]
INFO:tensorflow:Evaluation [83/100]
INFO:tensorflow:Evaluation [84/100]
INFO:tensorflow:Evaluation [85/100]
INFO:tensorflow:Evaluation [86/100]
INFO:tensorflow:Evaluation [87/100]
INFO:tensorflow:Evaluation [88/100]
INFO:tensorflow:Evaluation [89/100]
INFO:tensorflow:Evaluation [90/100]
INFO:tensorflow:Evaluation [91/100]
INFO:tensorflow:Evaluation [92/100]
INFO:tensorflow:Evaluation [93/100]
INFO:tensorflow:Evaluation [94/100]
INFO:tensorflow:Evaluation [95/100]
INFO:tensorflow:Evaluation [96/100]
INFO:tensorflow:Evaluation [97/100]
INFO:tensorflow:Evaluation [98/100]
INFO:tensorflow:Evaluation [99/100]
INFO:tensorflow:Evaluation [100/100]
INFO:tensorflow:Finished evaluation at 2017-05-31-00:26:01
INFO:tensorflow:Saving dict for global step 1: accuracy = 0.2614, global_step = 1, loss = 2.15361
INFO:tensorflow:Validation (step 1): loss = 2.15361, global_step = 1, accuracy = 0.2614
INFO:tensorflow:Saving checkpoints for 100 into ../../data/expt-tf-model/model.ckpt.
INFO:tensorflow:Loss for final step: 0.318277.
WARNING:tensorflow:From /Users/palsujit/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:625: scalar_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.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
INFO:tensorflow:Starting evaluation at 2017-05-31-00:30:48
INFO:tensorflow:Restoring parameters from ../../data/expt-tf-model/model.ckpt-100
INFO:tensorflow:Evaluation [1/100]
INFO:tensorflow:Evaluation [2/100]
INFO:tensorflow:Evaluation [3/100]
INFO:tensorflow:Evaluation [4/100]
INFO:tensorflow:Evaluation [5/100]
INFO:tensorflow:Evaluation [6/100]
INFO:tensorflow:Evaluation [7/100]
INFO:tensorflow:Evaluation [8/100]
INFO:tensorflow:Evaluation [9/100]
INFO:tensorflow:Evaluation [10/100]
INFO:tensorflow:Evaluation [11/100]
INFO:tensorflow:Evaluation [12/100]
INFO:tensorflow:Evaluation [13/100]
INFO:tensorflow:Evaluation [14/100]
INFO:tensorflow:Evaluation [15/100]
INFO:tensorflow:Evaluation [16/100]
INFO:tensorflow:Evaluation [17/100]
INFO:tensorflow:Evaluation [18/100]
INFO:tensorflow:Evaluation [19/100]
INFO:tensorflow:Evaluation [20/100]
INFO:tensorflow:Evaluation [21/100]
INFO:tensorflow:Evaluation [22/100]
INFO:tensorflow:Evaluation [23/100]
INFO:tensorflow:Evaluation [24/100]
INFO:tensorflow:Evaluation [25/100]
INFO:tensorflow:Evaluation [26/100]
INFO:tensorflow:Evaluation [27/100]
INFO:tensorflow:Evaluation [28/100]
INFO:tensorflow:Evaluation [29/100]
INFO:tensorflow:Evaluation [30/100]
INFO:tensorflow:Evaluation [31/100]
INFO:tensorflow:Evaluation [32/100]
INFO:tensorflow:Evaluation [33/100]
INFO:tensorflow:Evaluation [34/100]
INFO:tensorflow:Evaluation [35/100]
INFO:tensorflow:Evaluation [36/100]
INFO:tensorflow:Evaluation [37/100]
INFO:tensorflow:Evaluation [38/100]
INFO:tensorflow:Evaluation [39/100]
INFO:tensorflow:Evaluation [40/100]
INFO:tensorflow:Evaluation [41/100]
INFO:tensorflow:Evaluation [42/100]
INFO:tensorflow:Evaluation [43/100]
INFO:tensorflow:Evaluation [44/100]
INFO:tensorflow:Evaluation [45/100]
INFO:tensorflow:Evaluation [46/100]
INFO:tensorflow:Evaluation [47/100]
INFO:tensorflow:Evaluation [48/100]
INFO:tensorflow:Evaluation [49/100]
INFO:tensorflow:Evaluation [50/100]
INFO:tensorflow:Evaluation [51/100]
INFO:tensorflow:Evaluation [52/100]
INFO:tensorflow:Evaluation [53/100]
INFO:tensorflow:Evaluation [54/100]
INFO:tensorflow:Evaluation [55/100]
INFO:tensorflow:Evaluation [56/100]
INFO:tensorflow:Evaluation [57/100]
INFO:tensorflow:Evaluation [58/100]
INFO:tensorflow:Evaluation [59/100]
INFO:tensorflow:Evaluation [60/100]
INFO:tensorflow:Evaluation [61/100]
INFO:tensorflow:Evaluation [62/100]
INFO:tensorflow:Evaluation [63/100]
INFO:tensorflow:Evaluation [64/100]
INFO:tensorflow:Evaluation [65/100]
INFO:tensorflow:Evaluation [66/100]
INFO:tensorflow:Evaluation [67/100]
INFO:tensorflow:Evaluation [68/100]
INFO:tensorflow:Evaluation [69/100]
INFO:tensorflow:Evaluation [70/100]
INFO:tensorflow:Evaluation [71/100]
INFO:tensorflow:Evaluation [72/100]
INFO:tensorflow:Evaluation [73/100]
INFO:tensorflow:Evaluation [74/100]
INFO:tensorflow:Evaluation [75/100]
INFO:tensorflow:Evaluation [76/100]
INFO:tensorflow:Evaluation [77/100]
INFO:tensorflow:Evaluation [78/100]
INFO:tensorflow:Evaluation [79/100]
INFO:tensorflow:Evaluation [80/100]
INFO:tensorflow:Evaluation [81/100]
INFO:tensorflow:Evaluation [82/100]
INFO:tensorflow:Evaluation [83/100]
INFO:tensorflow:Evaluation [84/100]
INFO:tensorflow:Evaluation [85/100]
INFO:tensorflow:Evaluation [86/100]
INFO:tensorflow:Evaluation [87/100]
INFO:tensorflow:Evaluation [88/100]
INFO:tensorflow:Evaluation [89/100]
INFO:tensorflow:Evaluation [90/100]
INFO:tensorflow:Evaluation [91/100]
INFO:tensorflow:Evaluation [92/100]
INFO:tensorflow:Evaluation [93/100]
INFO:tensorflow:Evaluation [94/100]
INFO:tensorflow:Evaluation [95/100]
INFO:tensorflow:Evaluation [96/100]
INFO:tensorflow:Evaluation [97/100]
INFO:tensorflow:Evaluation [98/100]
INFO:tensorflow:Evaluation [99/100]
INFO:tensorflow:Evaluation [100/100]
INFO:tensorflow:Finished evaluation at 2017-05-31-00:31:07
INFO:tensorflow:Saving dict for global step 100: accuracy = 0.9152, global_step = 100, loss = 0.303028










    
Out[9]:








({'accuracy': 0.9152, 'global_step': 100, 'loss': 0.30302814}, [])

















In [ ]:

Content source: sujitpal/polydlot

Similar notebooks:

notebook.community | gallery | about