def runOutputLayerTests(self):
tests.test_output(output)
##############################
## Build the Neural Network ##
##############################
# Remove previous weights, bias, inputs, etc..
tests.test_conv_net(conv_net)
print("Model OutputLayerTests Ran Successfully")
def test_implementation():
tf.reset_default_graph()
tests.test_nn_image_inputs(neural_net_image_input)
tests.test_nn_label_inputs(neural_net_label_input)
tests.test_nn_keep_prob_inputs(neural_net_keep_prob_input)
tests.test_con_pool(conv2d_maxpool)
tests.test_flatten(flatten)
tests.test_fully_conn(fully_conn)
tests.test_output(output)
build_cnn()
tests.test_conv_net(conv_net)
tests.test_train_nn(train_neural_network)
def run_tests():
import problem_unittests as t
t.test_folder_path(cifar10_dataset_folder_path)
t.test_normalize(normalize)
t.test_one_hot_encode(one_hot_encode)
t.test_nn_image_inputs(neural_net_image_input)
t.test_nn_label_inputs(neural_net_label_input)
t.test_nn_keep_prob_inputs(neural_net_keep_prob_input)
t.test_con_pool(conv2conv2d_maxpool)
t.test_flatten(flatten)
t.test_fully_conn(fully_conn)
t.test_output(output)
t.test_conv_net(conv_net)
t.test_train_nn(train_neural_network)
# Model logits = conv_net(x, keep_prob) # Name logits Tensor, so that is can be loaded from disk after training logits = tf.identity(logits, name='logits') # Loss and Optimizer cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y)) optimizer = tf.train.AdamOptimizer().minimize(cost) # Accuracy correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32), name='accuracy') tests.test_conv_net(conv_net) # ## Train the Neural Network # ### Single Optimization # Implement the function `train_neural_network` to do a single optimization. The optimization should use `optimizer` to optimize in `session` with a `feed_dict` of the following: # * `x` for image input # * `y` for labels # * `keep_prob` for keep probability for dropout # # This function will be called for each batch, so `tf.global_variables_initializer()` has already been called. # # Note: Nothing needs to be returned. This function is only optimizing the neural network. # In[ ]:
# Model logits = conv_net(x, keep_prob) # Name logits Tensor, so that is can be loaded from disk after training logits = tf.identity(logits, name='logits') # Loss and Optimizer cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y)) optimizer = tf.train.AdamOptimizer().minimize(cost) # Accuracy correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32), name='accuracy') tests.test_conv_net(conv_net) # ## Train the Neural Network # ### Single Optimization # Implement the function `train_neural_network` to do a single optimization. The optimization should use `optimizer` to optimize in `session` with a `feed_dict` of the following: # * `x` for image input # * `y` for labels # * `keep_prob` for keep probability for dropout # # This function will be called for each batch, so `tf.global_variables_initializer()` has already been called. # # Note: Nothing needs to be returned. This function is only optimizing the neural network. # In[13]:
