float32
feature_names = [ 'SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth']
def input_fn(): ...<code>... return ({ 'SepalLength':[values], ..<etc>.., 'PetalWidth':[values] }, [IrisFlowerType])
input_fn
file_path
perform_shuffle
repeat_count
def my_input_fn(file_path, perform_shuffle=False, repeat_count=1): def decode_csv(line): parsed_line = tf.decode_csv(line, [[0.], [0.], [0.], [0.], [0]]) label = parsed_line[-1:] # Last element is the label del parsed_line[-1] # Delete last element features = parsed_line # Everything (but last element) are the features d = dict(zip(feature_names, features)), label return d dataset = (tf.contrib.data.TextLineDataset(file_path) # Read text file .skip(1) # Skip header row .map(decode_csv)) # Transform each elem by applying decode_csv fn if perform_shuffle: # Randomizes input using a window of 256 elements (read into memory) dataset = dataset.shuffle(buffer_size=256) dataset = dataset.repeat(repeat_count) # Repeats dataset this # times dataset = dataset.batch(32) # Batch size to use iterator = dataset.make_one_shot_iterator() batch_features, batch_labels = iterator.get_next() return batch_features, batch_labels
TextLineDataset
shuffle
map
decode_csv
next_batch = my_input_fn(FILE, True) # Will return 32 random elements # Now let's try it out, retrieving and printing one batch of data. # Although this code looks strange, you don't need to understand # the details. with tf.Session() as sess: first_batch = sess.run(next_batch) print(first_batch) # Output ({'SepalLength': array([ 5.4000001, ...], dtype=float32), 'PetalWidth': array([ 0.40000001, ...], dtype=float32), ... }, [array([[2], ...], dtype=int32) # Labels )
my_input_fn
# Create the feature_columns, which specifies the input to our model. # All our input features are numeric, so use numeric_column for each one. feature_columns = [tf.feature_column.numeric_column(k) for k in feature_names] # Create a deep neural network regression classifier. # Use the DNNClassifier pre-made estimator classifier = tf.estimator.DNNClassifier( feature_columns=feature_columns, # The input features to our model hidden_units=[10, 10], # Two layers, each with 10 neurons n_classes=3, model_dir=PATH) # Path to where checkpoints etc are stored
# Train our model, use the previously function my_input_fn # Input to training is a file with training example # Stop training after 8 iterations of train data (epochs) classifier.train( input_fn=lambda: my_input_fn(FILE_TRAIN, True, 8))
lambda: my_input_fn(FILE_TRAIN, True, 8)
lambda
file_path, shuffle setting,
my_input_fn,
FILE_TRAIN
True
8
evaluate
# Evaluate our model using the examples contained in FILE_TEST # Return value will contain evaluation_metrics such as: loss & average_loss evaluate_result = estimator.evaluate( input_fn=lambda: my_input_fn(FILE_TEST, False, 4) print("Evaluation results") for key in evaluate_result: print(" {}, was: {}".format(key, evaluate_result[key]))
model_dir=PATH
DNNClassifier
# Predict the type of some Iris flowers. # Let's predict the examples in FILE_TEST, repeat only once. predict_results = classifier.predict( input_fn=lambda: my_input_fn(FILE_TEST, False, 1)) print("Predictions on test file") for prediction in predict_results: # Will print the predicted class, i.e: 0, 1, or 2 if the prediction # is Iris Sentosa, Vericolor, Virginica, respectively. print prediction["class_ids"][0]
FILE_TEST
predict
# Let create a memory dataset for prediction. # We've taken the first 3 examples in FILE_TEST. prediction_input = [[5.9, 3.0, 4.2, 1.5], # -> 1, Iris Versicolor [6.9, 3.1, 5.4, 2.1], # -> 2, Iris Virginica [5.1, 3.3, 1.7, 0.5]] # -> 0, Iris Sentosa def new_input_fn(): def decode(x): x = tf.split(x, 4) # Need to split into our 4 features # When predicting, we don't need (or have) any labels return dict(zip(feature_names, x)) # Then build a dict from them # The from_tensor_slices function will use a memory structure as input dataset = tf.contrib.data.Dataset.from_tensor_slices(prediction_input) dataset = dataset.map(decode) iterator = dataset.make_one_shot_iterator() next_feature_batch = iterator.get_next() return next_feature_batch, None # In prediction, we have no labels # Predict all our prediction_input predict_results = classifier.predict(input_fn=new_input_fn) # Print results print("Predictions on memory data") for idx, prediction in enumerate(predict_results): type = prediction["class_ids"][0] # Get the predicted class (index) if type == 0: print("I think: {}, is Iris Sentosa".format(prediction_input[idx])) elif type == 1: print("I think: {}, is Iris Versicolor".format(prediction_input[idx])) else: print("I think: {}, is Iris Virginica".format(prediction_input[idx])
Dataset.from_tensor_slides()
# Replace PATH with the actual path passed as model_dir argument when the # DNNRegressor estimator was created. tensorboard --logdir=PATH
