def simple_net(x):
# 3. Define weight and bias variables using tf.Variable
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
# 3. Define weight and bias variables using tf.Variable
logits = tf.matmul(x, W) + b
y = tf.nn.softmax(logits)
return y
if __name__ == '__main__':
# 1. Load data using lab utils/get brain body data
mnist_data = get_mnist_data("./data/", one_hot=True, verbose=True)
print("mnist_data: " + str(mnist_data))
# 2. Define appropriate placeholders using tf.placeholder
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
# Create the model
y = simple_net(x)
# Define loss and optimizer
eps = np.finfo("float32").eps
loss = tf.reduce_mean(tf.reduce_sum(y_ * -1 * tf.log(y + eps),
1)) # acc=0,66 senza rediction_indices
#cross_entropy_loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
initial_value=tf.random_normal(shape=[hidden_dim, n_classes]),
name='l2_weights')
b_2 = tf.Variable(initial_value=tf.zeros(shape=[n_classes]),
name='l2_biases')
logits = tf.matmul(hidden_1, W_2) + b_2
y = tf.nn.softmax(logits)
return y
if __name__ == '__main__':
# Load MNIST data
mnist = get_mnist_data('/tmp/mnist', verbose=True)
# Placeholders
x = tf.placeholder(dtype=tf.float32, shape=[None,
784]) # input placeholder
# Placeholder for targets
targets = tf.placeholder(dtype=tf.float32, shape=[None, 10])
# Define model output
y = multi_layer_net(x)
# Define loss function
loss = tf.reduce_mean(
-tf.reduce_sum(targets * tf.log(y + EPS), reduction_indices=1))