基于CNN的车牌（字符）识别 plate recognition using CNN based on Tensorflow

# ============================================================================== """Simple, end-to-end, LeNet-5-like convolutional MNIST model example. This should achieve a test error of 0.7%. Please keep this model as simple and linear as possible, it is meant as a tutorial for simple convolutional models. Run with --self_test on the command line to execute a short self-test. """ from __future__ import absolute_import from __future__ import division from __future__ import print_function import gzip import os import sys import time import numpy from six.moves import urllib from six.moves import xrange # pylint: disable=redefined-builtin import tensorflow as tf from load_data import read_data_sets as input_data WORK_DIRECTORY = 'data' ROW = 80 COL = 120 IMAGE_SIZE = 28 NUM_CHANNELS = 1 PIXEL_DEPTH = 255 NUM_LABELS = 10 VALIDATION_SIZE = 50 # Size of the validation set. SEED = 66478 # Set to None for random seed. BATCH_SIZE = 500 NUM_EPOCHS = 900 EVAL_BATCH_SIZE = 100 EVAL_FREQUENCY = 300 # Number of steps between evaluations. tf.app.flags.DEFINE_boolean("self_test", False, "True if running a self test.") tf.app.flags.DEFINE_boolean('use_fp16', False, "Use half floats instead of full floats if True.") FLAGS = tf.app.flags.FLAGS def data_type(): """Return the type of the activations, weights, and placeholder variables.""" if FLAGS.use_fp16: return tf.float16 else: return tf.float32 def maybe_download(filename): """Download the data from Yann's website, unless it's already here.""" if not tf.gfile.Exists(WORK_DIRECTORY): tf.gfile.MakeDirs(WORK_DIRECTORY) filepath = os.path.join(WORK_DIRECTORY, filename) if not tf.gfile.Exists(filepath): filepath, _ = urllib.request.urlretrieve(SOURCE_URL + filename, filepath) with tf.gfile.GFile(filepath) as f: size = f.Size() print('Successfully downloaded', filename, size, 'bytes.') return filepath def extract_data(filename, num_images): """Extract the images into a 4D tensor [image index, y, x, channels]. Values are rescaled from [0, 255] down to [-0.5, 0.5]. """ print('Extracting', filename) with gzip.open(filename) as bytestream: bytestream.read(16) buf = bytestream.read(IMAGE_SIZE * IMAGE_SIZE * num_images * NUM_CHANNELS) data = numpy.frombuffer(buf, dtype=numpy.uint8).astype(numpy.float32) data = (data - (PIXEL_DEPTH / 2.0)) / PIXEL_DEPTH data = data.reshape(num_images, IMAGE_SIZE, IMAGE_SIZE, NUM_CHANNELS) return data def extract_labels(filename, num_images): """Extract the labels into a vector of int64 label IDs.""" print('Extracting', filename) with gzip.open(filename) as bytestream: bytestream.read(8) buf = bytestream.read(1 * num_images) labels = numpy.frombuffer(buf, dtype=numpy.uint8).astype(numpy.int64) return labels def fake_data(num_images): """Generate a fake dataset that matches the dimensions of MNIST.""" data = numpy.ndarray( shape=(num_images, IMAGE_SIZE, IMAGE_SIZE, NUM_CHANNELS), dtype=numpy.float32) labels = numpy.zeros(shape=(num_images,), dtype=numpy.int64) for image in xrange(num_images): label = image % 2 data[image, :, :, 0] = label - 0.5 labels[image] = label return data, labels def error_rate(predictions, labels): """Return the error rate based on dense predictions and sparse labels.""" return 100.0 - ( 100.0 * numpy.sum(numpy.argmax(predictions, 1) == labels) / predictions.shape[0]) def main(argv=None): # pylint: disable=unused-argument if FLAGS.self_test: print('Running self-test.') train_data, train_labels = fake_data(256) validation_data, validation_labels = fake_data(EVAL_BATCH_SIZE) test_data, test_labels = fake_data(EVAL_BATCH_SIZE) num_epochs = 1 else: # Get the data. # Extract it into numpy arrays. # Generate a validation set. mnist = input_data(train_dir='/home/a/workspace/ssd/DataSets/mnist_120/',\ test_dir='/home/a/workspace/ssd/DataSets/mnist_120_test/',\ num_class=10, one_hot=False) train_data = mnist.train.images train_labels = mnist.train.labels test_data = mnist.test.images test_labels = mnist.test.labels validation_data = mnist.validation.images validation_labels= mnist.validation.labels num_epochs = NUM_EPOCHS train_size = train_labels.shape[0] # This is where training samples and labels are fed to the graph. # These placeholder nodes will be fed a batch of training data at each # training step using the {feed_dict} argument to the Run() call below. train_data_node = tf.placeholder( data_type(), shape=(BATCH_SIZE, ROW, COL, NUM_CHANNELS)) train_labels_node = tf.placeholder(tf.int64, shape=(BATCH_SIZE,)) eval_data = tf.placeholder( data_type(), shape=(EVAL_BATCH_SIZE, ROW, COL, NUM_CHANNELS)) # The variables below hold all the trainable weights. They are passed an # initial value which will be assigned when we call: # {tf.initialize_all_variables().run()} conv1_weights = tf.Variable( tf.truncated_normal([5, 5, NUM_CHANNELS, 32], # 5x5 filter, depth 32. stddev=0.1, seed=SEED, dtype=data_type())) conv1_biases = tf.Variable(tf.zeros([32], dtype=data_type())) conv2_weights = tf.Variable(tf.truncated_normal( [5, 5, 32, 64], stddev=0.1, seed=SEED, dtype=data_type())) conv2_biases = tf.Variable(tf.constant(0.1, shape=[64], dtype=data_type())) fc1_weights = tf.Variable( # fully connected, depth 512. tf.truncated_normal([ROW // 4 * COL // 4 * 64, 512], stddev=0.1, seed=SEED, dtype=data_type())) fc1_biases = tf.Variable(tf.constant(0.1, shape=[512], dtype=data_type())) fc2_weights = tf.Variable(tf.truncated_normal([512, NUM_LABELS], stddev=0.1, seed=SEED, dtype=data_type())) fc2_biases = tf.Variable(tf.constant( 0.1, shape=[NUM_LABELS], dtype=data_type())) # We will replicate the model structure for the training subgraph, as well # as the evaluation subgraphs, while sharing the trainable parameters. def model(data, train=False): """The Model definition.""" # 2D convolution, with 'SAME' padding (i.e. the output feature map has # the same size as the input). Note that {strides} is a 4D array whose # shape matches the data layout: [image index, y, x, depth]. conv = tf.nn.conv2d(data, conv1_weights, strides=[1, 1, 1, 1], padding='SAME') # Bias and rectified linear non-linearity. relu = tf.nn.relu(tf.nn.bias_add(conv, conv1_biases)) # Max pooling. The kernel size spec {ksize} also follows the layout of # the data. Here we have a pooling window of 2, and a stride of 2. pool = tf.nn.max_pool(relu, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') conv = tf.nn.conv2d(pool, conv2_weights, strides=[1, 1, 1, 1], padding='SAME') relu = tf.nn.relu(tf.nn.bias_add(conv, conv2_biases)) pool = tf.nn.max_pool(relu, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') # Reshape the feature map cuboid into a 2D matrix to feed it to the # fully connected layers. pool_shape = pool.get_shape().as_list() reshape = tf.reshape( pool, [pool_shape[0], pool_shape[1] * pool_shape[2] * pool_shape[3]]) # Fully connected layer. Note that the '+' operation automatically # broadcasts the biases. hidden = tf.