def eval_cnn_model():
eval_data, eval_data_labels, filelist = read_img_file('eval')
# evaluate the model and print results
eval_input_fn = tf.estimator.inputs.numpy_input_fn(x={"x": eval_data},
y=eval_data_labels,
num_epochs=1,
shuffle=False)
eval_results = cnn_symbol_classifier.evaluate(input_fn=eval_input_fn)
print(eval_results)
def train_cnn_model(steps):
train_data, train_data_labels = read_img_file('train')
# set up logging for predictions
# log the values in the "softmax" tensor with label "probabilities"
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log,
every_n_iter=50)
# train the model
train_input_fn = tf.estimator.inputs.numpy_input_fn(x={"x": train_data},
y=train_data_labels,
batch_size=100,
num_epochs=None,
shuffle=True)
print(train_input_fn)
cnn_symbol_classifier.train(input_fn=train_input_fn,
steps=steps,
hooks=[logging_hook])