def extract_features(self, inputs): with tf.variable_scope('fcn_16s'): with slim.arg_scope( vgg.vgg_arg_scope(weight_decay=self._weight_decay)): fc8_logits, end_points = vgg.vgg_16( inputs=inputs, num_classes=self._num_classes, is_training=self._is_training, spatial_squeeze=self._spatial_squeeze, fc_conv_padding='SAME', global_pool=self._global_pool) upsampled_fc8_logits = slim.conv2d_transpose( fc8_logits, self._num_classes, kernel_size=[4, 4], stride=[2, 2], padding='SAME', activation_fn=None, normalizer_fn=None, scope='deconv1') pool4 = end_points['fcn_16s/vgg_16/pool4'] pool4_logits = slim.conv2d( pool4, self._num_classes, [1, 1], activation_fn=None, normalizer_fn=None, scope='pool4_conv') fused_logits = tf.add(pool4_logits, upsampled_fc8_logits, name='fused_logits') logits = tf.image.resize_bilinear( fused_logits, tf.shape(inputs)[1:3], align_corners=True) return logits
def predict(models_path, image_dir, labels_filename, labels_nums, data_format): [batch_size, resize_height, resize_width, depths] = data_format labels = np.loadtxt(labels_filename, str, delimiter='\t') input_images = tf.placeholder( dtype=tf.float32, shape=[None, resize_height, resize_width, depths], name='input') with slim.arg_scope(vgg.vgg_arg_scope()): out, end_points = vgg.vgg_16(inputs=input_images, num_classes=labels_nums, dropout_keep_prob=1.0, is_training=False) # 将输出结果进行softmax分布,再求最大概率所属类别 sess = tf.InteractiveSession() sess.run(tf.global_variables_initializer()) saver = tf.train.Saver() saver.restore(sess, models_path) images_list = glob.glob(os.path.join(image_dir, '*.jpg')) for image_path in images_list: im = read_image(image_path, resize_height, resize_width, normalization=True) im = im[np.newaxis, :] #pred = sess.run(f_cls, feed_dict={x:im, keep_prob:1.0}) pre_score = sess.run([out], feed_dict={input_images: im}) print "image_path:{},pre_score:{}".format(image_path, pre_score) sess.close()
def extract_features(self, inputs): with slim.arg_scope( vgg.vgg_arg_scope(weight_decay=self._weight_decay)): with tf.variable_scope('fcn_32s'): fc8_logits, end_points = vgg.vgg_16( inputs=inputs, num_classes=self._num_classes, is_training=self._is_training, spatial_squeeze=self._spatial_squeeze, fc_conv_padding='SAME', global_pool=self._global_pool) logits = tf.image.resize_bilinear( fc8_logits, tf.shape(inputs)[1:3], align_corners=True) return logits
def predict(models_path, image_dir, labels_filename, labels_nums, data_format): [batch_size, resize_height, resize_width, depths] = data_format #labels = np.loadtxt(labels_filename, str, delimiter='\t') input_images = tf.placeholder( dtype=tf.float32, shape=[None, resize_height, resize_width, depths], name='input') #其他模型预测请修改这里 with slim.arg_scope(vgg.vgg_arg_scope()): out, end_points = vgg.vgg_16(inputs=input_images, num_classes=labels_nums, dropout_keep_prob=1.0, is_training=False) # 将输出结果进行softmax分布,再求最大概率所属类别 score = tf.nn.softmax(out, name='pre') class_id = tf.argmax(score, 1) sess = tf.InteractiveSession() sess.run(tf.global_variables_initializer()) saver = tf.train.Saver() saver.restore(sess, models_path) images_list = glob.glob(os.path.join(image_dir, '*.jpg')) for image_path in images_list: im = read_image(image_path, resize_height, resize_width, normalization=True) im = im[np.newaxis, :] #pred = sess.run(f_cls, feed_dict={x:im, keep_prob:1.0}) pre_score, pre_label = sess.run([score, class_id], feed_dict={input_images: im}) max_score = pre_score[0, pre_label] print("{} is: pre labels:{},name:{} score: {}".format( image_path, pre_label, list(labels_filename.keys())[list( labels_filename.values()).index(pre_label)], max_score)) sess.close()
def train(train_filename, train_images_dir, train_log_step, train_param, val_filename, val_images_dir, val_log_step, labels_nums, data_shape, snapshot, snapshot_prefix): ''' :param train_record_file: 训练的tfrecord文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param val_record_file: 验证的tfrecord文件 :param val_log_step: 显示验证过程log信息间隔 :param val_param: val参数 :param labels_nums: labels数 :param data_shape: 输入数据shape :param snapshot: 保存模型间隔 :param snapshot_prefix: 保存模型文件的前缀名 :return: ''' [base_lr, max_steps] = train_param [batch_size, resize_height, resize_width, depths] = data_shape # # 从record中读取图片和labels数据 tf_image, tf_labels = read_images(train_filename, train_images_dir, data_shape, shuffle=True, type='normalization') train_images_batch, train_labels_batch = get_batch_images( tf_image, tf_labels, batch_size=batch_size, labels_nums=labels_nums, one_hot=False, shuffle=True) # Define the model: with slim.arg_scope(vgg.vgg_arg_scope()): out, end_points = vgg.vgg_16(inputs=input_images, num_classes=labels_nums, dropout_keep_prob=keep_prob, is_training=is_training) loss = tf.reduce_sum(tf.squared_difference(x=out, y=input_labels)) # loss1=tf.squared_difference(x=out,y=input_labels) # loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=output, labels=y)) train_op = tf.train.AdamOptimizer(learning_rate=base_lr).minimize(loss) # tf.losses.add_loss(loss1) # # slim.losses.add_loss(my_loss) # loss = tf.losses.get_total_loss(add_regularization_losses=True) # 添加正则化损失loss=2.2 # # Specify the optimization scheme: # optimizer = tf.train.GradientDescentOptimizer(learning_rate=base_lr) # # create_train_op that ensures that when we evaluate it to get the loss, # # the update_ops are done and the gradient updates are computed. # train_op = slim.learning.create_train_op(total_loss=loss, optimizer=optimizer) saver = tf.train.Saver(max_to_keep=4) max_acc = 0.0 with tf.Session() as sess: sess.run(tf.global_variables_initializer()) sess.run(tf.local_variables_initializer()) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) for i in range(max_steps + 1): batch_input_images, batch_input_labels = sess.run( [train_images_batch, train_labels_batch]) _, train_loss = sess.run( [train_op, loss], feed_dict={ input_images: batch_input_images, input_labels: batch_input_labels, keep_prob: 0.5, is_training: True }) if i % train_log_step == 0: print("%s: Step [%d] train Loss : %f" % (datetime.now(), i, train_loss)) # # train测试(这里仅测试训练集的一个batch) # if i%train_log_step == 0: # train_acc = sess.run(accuracy, feed_dict={input_images:batch_input_images, # input_labels: batch_input_labels, # keep_prob:1.0, is_training: False}) # print "%s: Step [%d] train Loss : %f, training accuracy : %g" % (datetime.now(), i, train_loss, train_acc) # # # val测试(测试全部val数据) # if i%val_log_step == 0: # _, train_loss = sess.run([train_step, loss], feed_dict={input_images: batch_input_images, # input_labels: batch_input_labels, # keep_prob: 1.0, is_training: False}) # print "%s: Step [%d] val Loss : %f, val accuracy : %g" % (datetime.now(), i, mean_loss, mean_acc) # # 模型保存:每迭代snapshot次或者最后一次保存模型 if (i % snapshot == 0 and i > 0) or i == max_steps: print('-----save:{}-{}'.format(snapshot_prefix, i)) saver.save(sess, snapshot_prefix, global_step=i) # # 保存val准确率最高的模型 # if mean_acc>max_acc and mean_acc>0.5: # max_acc=mean_acc # path = os.path.dirname(snapshot_prefix) # best_models=os.path.join(path,'best_models_{}_{:.4f}.ckpt'.format(i,max_acc)) # print('------save:{}'.format(best_models)) # saver.save(sess, best_models) coord.request_stop() coord.join(threads)
def train(data_csv_path_train, train_log_step, train_param, data_csv_path_val, val_log_step, labels_nums, data_shape, snapshot, snapshot_prefix): ''' :param data_csv_path_train: 训练的csv文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param data_csv_path_val: 验证的val文件 :param val_log_step: 显示验证过程log信息间隔 :param val_param: val参数 :param labels_nums: labels数 :param data_shape: 输入数据shape :param snapshot: 保存模型间隔 :param snapshot_prefix: 保存模型文件的前缀名 :return: ''' [base_lr, max_steps] = train_param [batch_size, resize_height, resize_width, depths] = data_shape # 获得训练和测试的样本数 with open(dataset_csv_path_train, 'r') as f: train_nums = len(f.readlines()) with open(dataset_csv_path_val, 'r') as v: val_nums = len(v.readlines()) print('train nums:%d,val nums:%d' % (train_nums, val_nums)) train_batch = data_loader.load_data(data_csv_path_train, image_type=args.image_type, image_size_before_crop=resize_height, labels_nums=labels_nums) train_images_batch = train_batch['image'] train_labels_batch = train_batch['label'] # print('......................................................') # print(train_images_batch) # print(train_labels_batch) # val数据,验证数据可以不需要打乱数据 val_batch = data_loader.load_data(data_csv_path_val, image_type=args.image_type, image_size_before_crop=resize_height, labels_nums=labels_nums, do_shuffle=False) val_images_batch = val_batch['image'] val_labels_batch = val_batch['label'] # Define the model: with slim.arg_scope(vgg.vgg_arg_scope()): out, end_points = vgg.vgg_16(inputs=input_images, num_classes=labels_nums, dropout_keep_prob=keep_prob, is_training=is_training) # Specify the loss function: tf.losses定义的loss函数都会自动添加到loss函数,不需要add_loss()了 tf.losses.softmax_cross_entropy(onehot_labels=input_labels, logits=out) #添加交叉熵损失loss=1.6 # slim.losses.add_loss(my_loss) loss = tf.losses.get_total_loss( add_regularization_losses=False) #添加正则化损失loss=2.2 accuracy = tf.reduce_mean( tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(input_labels, 1)), tf.float32)) # Specify the optimization scheme: # optimizer = tf.train.GradientDescentOptimizer(learning_rate=base_lr) # global_step = tf.Variable(0, trainable=False) # learning_rate = tf.train.exponential_decay(0.05, global_step, 150, 0.9) # optimizer = tf.train.MomentumOptimizer(learning_rate=base_lr,momentum= 0.9) optimizer = tf.train.GradientDescentOptimizer(learning_rate=base_lr) # # train_tensor = optimizer.minimize(loss, global_step) # train_op = slim.learning.create_train_op(loss, optimizer,global_step=global_step) # 在定义训练的时候, 注意到我们使用了`batch_norm`层时,需要更新每一层的`average`和`variance`参数, # 更新的过程不包含在正常的训练过程中, 需要我们去手动像下面这样更新 # 通过`tf.get_collection`获得所有需要更新的`op` update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) # 使用`tensorflow`的控制流, 先执行更新算子, 再执行训练 with tf.control_dependencies(update_ops): # create_train_op that ensures that when we evaluate it to get the loss, # the update_ops are done and the gradient updates are computed. # train_op = slim.learning.create_train_op(total_loss=loss,optimizer=optimizer) train_op = slim.learning.create_train_op(total_loss=loss, optimizer=optimizer) # 循环迭代过程 step_train(train_op, loss, accuracy, train_images_batch, train_labels_batch, train_nums, train_log_step, val_images_batch, val_labels_batch, val_nums, val_log_step, snapshot_prefix, snapshot)
#################### 改这里 ######################################## #导入模型 from slim.nets.vgg import vgg_16 from slim.nets.vgg import vgg_arg_scope #要测试的如数尺寸 input_size = [224, 224, 3] # 给模型的输入口 inputs = tf.placeholder(tf.float32, shape=(1, input_size[0], input_size[1], input_size[2])) num_class = 32 #建造模型 with slim.arg_scope(vgg_arg_scope()): net, end_points = vgg_16(inputs, num_class) #只要有logits就可以评估了,中间过程layers_end_points有的话就显示,没有就不显示 logits = net layers_end_points = end_points #################### end ########################################### def show_parament_numbers(): from functools import reduce from operator import mul def get_num_params(): num_params = 0
def train(train_record_file, train_log_step, train_param, val_record_file, val_log_step, labels_nums, data_shape, snapshot, snapshot_prefix): ''' :param train_record_file: 训练的tfrecord文件 :param train_log_step: 显示训练过程log信息间隔 :param train_param: train参数 :param val_record_file: 验证的tfrecord文件 :param val_log_step: 显示验证过程log信息间隔 :param val_param: val参数 :param labels_nums: labels数 :param data_shape: 输入数据shape :param snapshot: 保存模型间隔 :param snapshot_prefix: 保存模型文件的前缀名 :return: ''' [base_lr, max_steps] = train_param [batch_size, resize_height, resize_width, depths] = data_shape # 获得训练和测试的样本数 train_nums = get_example_nums(train_record_file) val_nums = get_example_nums(val_record_file) print('train nums:%d,val nums:%d' % (train_nums, val_nums)) # 从record中读取图片和labels数据 # train数据,训练数据一般要求打乱顺序shuffle=True train_images, train_labels = read_records(train_record_file, resize_height, resize_width, type='normalization') train_images_batch, train_labels_batch = get_batch_images( train_images, train_labels, batch_size=batch_size, labels_nums=labels_nums, one_hot=True, shuffle=True) # val数据,验证数据可以不需要打乱数据 val_images, val_labels = read_records(val_record_file, resize_height, resize_width, type='normalization') val_images_batch, val_labels_batch = get_batch_images( val_images, val_labels, batch_size=batch_size, labels_nums=labels_nums, one_hot=True, shuffle=False) # Define the model: with slim.arg_scope(vgg.vgg_arg_scope()): out, end_points = vgg.vgg_16(inputs=input_images, num_classes=labels_nums, dropout_keep_prob=keep_prob, is_training=is_training) # Specify the loss function: tf.losses定义的loss函数都会自动添加到loss函数,不需要add_loss()了 tf.losses.softmax_cross_entropy(onehot_labels=input_labels, logits=out) #添加交叉熵损失loss=1.6 # slim.losses.add_loss(my_loss) loss = tf.losses.get_total_loss( add_regularization_losses=True) #添加正则化损失loss=2.2 accuracy = tf.reduce_mean( tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(input_labels, 1)), tf.float32)) # Specify the optimization scheme: optimizer = tf.train.GradientDescentOptimizer(learning_rate=base_lr) # create_train_op that ensures that when we evaluate it to get the loss, # the update_ops are done and the gradient updates are computed. train_op = slim.learning.create_train_op(total_loss=loss, optimizer=optimizer) # global_step = tf.Variable(0, trainable=False) # learning_rate = tf.train.exponential_decay(0.05, global_step, 150, 0.9) # # optimizer = tf.train.MomentumOptimizer(learning_rate, 0.9) # # train_op = optimizer.minimize(loss, global_step) # train_op = slim.learning.create_train_op(loss, optimizer,global_step=global_step) saver = tf.train.Saver() max_acc = 0.0 with tf.Session() as sess: sess.run(tf.global_variables_initializer()) sess.run(tf.local_variables_initializer()) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) for i in range(max_steps + 1): batch_input_images, batch_input_labels = sess.run( [train_images_batch, train_labels_batch]) _, train_loss = sess.run( [train_op, loss], feed_dict={ input_images: batch_input_images, input_labels: batch_input_labels, keep_prob: 0.5, is_training: True }) # train测试(这里仅测试训练集的一个batch) if i % train_log_step == 0: train_acc = sess.run(accuracy, feed_dict={ input_images: batch_input_images, input_labels: batch_input_labels, keep_prob: 1.0, is_training: False }) print( "%s: Step [%d] train Loss : %f, training accuracy : %g" % (datetime.now(), i, train_loss, train_acc)) # val测试(测试全部val数据) if i % val_log_step == 0: mean_loss, mean_acc = net_evaluation(sess, loss, accuracy, val_images_batch, val_labels_batch, val_nums) print("%s: Step [%d] val Loss : %f, val accuracy : %g" % (datetime.now(), i, mean_loss, mean_acc)) # 模型保存:每迭代snapshot次或者最后一次保存模型 if (i % snapshot == 0 and i > 0) or i == max_steps: print('-----save:{}-{}'.format(snapshot_prefix, i)) saver.save(sess, snapshot_prefix, global_step=i) # 保存val准确率最高的模型 if mean_acc > max_acc and mean_acc > 0.5: max_acc = mean_acc path = os.path.dirname(snapshot_prefix) best_models = os.path.join( path, 'best_models_{}_{:.4f}.ckpt'.format(i, max_acc)) print('------save:{}'.format(best_models)) saver.save(sess, best_models) coord.request_stop() coord.join(threads)