def main():
# We treat images as sequences of pixel rows.
train, test = sets.Mnist()
_, rows, row_size = train.data.shape
num_classes = train.target.shape[1]
data = tf.placeholder(tf.float32, [None, rows, row_size])
target = tf.placeholder(tf.float32, [None, num_classes])
dropout = tf.placeholder(tf.float32)
model = SequenceClassification(data, target, dropout)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for epoch in range(10):
for _ in range(100):
batch = train.sample(10)
sess.run(model.optimize, {
data: batch.data,
target: batch.target,
dropout: 0.5
})
error = sess.run(model.error, {
data: test.data,
target: test.target,
dropout: 1
})
print('Epoch {:2d} error {:3.1f}%'.format(epoch + 1, 100 * error))
weight = tf.random.truncated_normal([in_size, out_size], stddev=0.01)
bias = tf.constant(0.1, shape=[out_size])
return tf.Variable(weight), tf.Variable(bias)
@staticmethod
def _last_relevant(output, length):
batch_size = tf.shape(input=output)[0]
max_length = int(output.get_shape()[1])
output_size = int(output.get_shape()[2])
index = tf.range(0, batch_size) * max_length + (length - 1)
flat = tf.reshape(output, [-1, output_size])
relevant = tf.gather(flat, index)
return relevant
if __name__ == '__main__':
# We treat images as sequences of pixel rows.
train, test = sets.Mnist()
_, rows, row_size = train.data.shape
num_classes = train.target.shape[1]
data = tf.compat.v1.placeholder(tf.float32, [None, rows, row_size])
target = tf.compat.v1.placeholder(tf.float32, [None, num_classes])
model = VariableSequenceClassification(data, target)
sess = tf.compat.v1.Session()
sess.run(tf.compat.v1.initialize_all_variables())
for epoch in range(10):
for _ in range(100):
batch = train.sample(10)
sess.run(model.optimize, {data: batch.data, target: batch.target})
error = sess.run(model.error, {data: test.data, target: test.target})
print('Epoch {:2d} error {:3.1f}%'.format(epoch + 1, 100 * error))