我已经下载了一个用于图像分割的FCN代码并且运行良好。现在我想添加一个rnn层，试图根据“ReSeg：基于回归神经网络的语义分割模型”的工作来优化结果。我的代码如下所示：
这部分用于推理：
def inference(image, keep_prob):
"""
Semantic segmentation network definition
:param image: input image. Should have values in range 0-255
:param keep_prob:
:return:
"""
print("setting up vgg initialized conv layers ...")
#model_data = utils.get_model_data(FLAGS.model_dir, MODEL_URL)
model_data = scipy.io.loadmat("H:/Deep Learning/FCN.tensorflow-master/imagenet-vgg-verydeep-19.mat")
mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
weights = np.squeeze(model_data['layers'])
processed_image = utils.process_image(image, mean_pixel)
with tf.variable_scope("inference"):
image_net = vgg_net(weights, processed_image)
conv_final_layer = image_net["conv5_3"]
pool5 = utils.max_pool_2x2(conv_final_layer)
W6 = utils.weight_variable([7, 7, 512, 4096], name="W6")
b6 = utils.bias_variable([4096], name="b6")
conv6 = utils.conv2d_basic(pool5, W6, b6)
relu6 = tf.nn.relu(conv6, name="relu6")
if FLAGS.debug:
utils.add_activation_summary(relu6)
relu_dropout6 = tf.nn.dropout(relu6, keep_prob=keep_prob)
W7 = utils.weight_variable([1, 1, 4096, 4096], name="W7")
b7 = utils.bias_variable([4096], name="b7")
conv7 = utils.conv2d_basic(relu_dropout6, W7, b7)
relu7 = tf.nn.relu(conv7, name="relu7")
if FLAGS.debug:
utils.add_activation_summary(relu7)
relu_dropout7 = tf.nn.dropout(relu7, keep_prob=keep_prob)
W8 = utils.weight_variable([1, 1, 4096, NUM_OF_CLASSESS], name="W8")
b8 = utils.bias_variable([NUM_OF_CLASSESS], name="b8")
conv8 = utils.conv2d_basic(relu_dropout7, W8, b8)
# annotation_pred1 = tf.argmax(conv8, dimension=3, name="prediction1")
# now to upscale to actual image size
deconv_shape1 = image_net["pool4"].get_shape()
W_t1 = utils.weight_variable([4, 4, deconv_shape1[3].value, NUM_OF_CLASSESS], name="W_t1")
b_t1 = utils.bias_variable([deconv_shape1[3].value], name="b_t1")
conv_t1 = utils.conv2d_transpose_strided(conv8, W_t1, b_t1, output_shape=tf.shape(image_net["pool4"]))
#fuse_1 = tf.add(conv_t1, image_net["pool4"], name="fuse_1")
deconv_shape2 = image_net["pool3"].get_shape()
W_t2 = utils.weight_variable([4, 4, deconv_shape2[3].value, deconv_shape1[3].value], name="W_t2")
b_t2 = utils.bias_variable([deconv_shape2[3].value], name="b_t2")
conv_t2 = utils.conv2d_transpose_strided(conv_t1, W_t2, b_t2, output_shape=tf.shape(image_net["pool3"]))
#fuse_2 = tf.add(conv_t2, image_net["pool3"], name="fuse_2")
shape = tf.shape(image)
deconv_shape3 = tf.stack([shape[0], shape[1], shape[2], NUM_OF_CLASSESS])
W_t3 = utils.weight_variable([16, 16, NUM_OF_CLASSESS, deconv_shape2[3].value], name="W_t3")
b_t3 = utils.bias_variable([NUM_OF_CLASSESS], name="b_t3")
conv_t3 = utils.conv2d_transpose_strided(conv_t2, W_t3, b_t3, output_shape=deconv_shape3, stride=8)
/////////////////////////////////////////////////////this is from where i added the rnn
shape_5 = tf.shape(image)
W_a = 224
H_a = 224
p_size_a = NUM_OF_CLASSESS
# x = tf.reshape(conv_t1, [shape_5[0],H_a,W_a, p_size_a])
x = tf.transpose(conv_t3, perm=[0,2,1,3])
x = tf.reshape(x,[-1,H_a,p_size_a])
mat = tf.unstack(x, H_a, 1)
lstm_fw_cell = rnn.BasicLSTMCell(N_HIDDEN, forget_bias=1.0)
lstm_bw_cell = rnn.BasicLSTMCell(N_HIDDEN, forget_bias=1.0)
#with tf.variable_scope('rnn1_1'):
try:
outputs, _, _ = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, mat,
dtype=tf.float32,scope='rnn1_1')
except Exception: # Old TensorFlow version only returns outputs not states
outputs = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, mat,
dtype=tf.float32)
outputs1 = tf.reshape(outputs,[H_a, shape_5[0], W_a, 2 * N_HIDDEN])
outputs1 = tf.transpose(outputs1,(1,0,2,3))
x_1 = tf.reshape(outputs1,[-1,W_a,2 * N_HIDDEN])
mat_1 = tf.unstack(x_1, W_a, 1)
lstm_lw_cell = rnn.BasicLSTMCell(N_HIDDEN, forget_bias=1.0)
lstm_rw_cell = rnn.BasicLSTMCell(N_HIDDEN, forget_bias=1.0)
#with tf.variable_scope('rnn1_2'):
try:
outputs2, _, _ = rnn.static_bidirectional_rnn(lstm_lw_cell, lstm_rw_cell, mat_1,
dtype=tf.float32,scope = 'rnn1_2')
except Exception: # Old TensorFlow version only returns outputs not states
outputs2 = rnn.static_bidirectional_rnn(lstm_lw_cell, lstm_rw_cell, mat_1,
dtype=tf.float32)
outputs2 = tf.reshape(outputs,[W_a, shape_5[0], H_a, 2 * N_HIDDEN])
outputs2 = tf.transpose(outputs2,(1,2,0,3))
///////////////////////////////////////////////////till here
annotation_pred = tf.argmax(outputs2, dimension=3, name="prediction")
return tf.expand_dims(annotation_pred, dim=3), outputs2
这部分用于培训：
def train(loss_val, var_list):
optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate)
grads = optimizer.compute_gradients(loss_val, var_list=var_list)
if FLAGS.debug:
# print(len(var_list))
for grad, var in grads:
utils.add_gradient_summary(grad, var)
return optimizer.apply_gradients(grads)
def main(argv=None):
keep_probability = tf.placeholder(tf.float32, name="keep_probabilty")
image = tf.placeholder(tf.float32, shape=[None, IMAGE_SIZE, IMAGE_SIZE, 3], name="input_image")
annotation = tf.placeholder(tf.int32, shape=[None, IMAGE_SIZE, IMAGE_SIZE, 1], name="annotation")
pred_annotation, logits = inference(image, keep_probability)
tf.summary.image("input_image", image, max_outputs=2)
tf.summary.image("ground_truth", tf.cast(annotation, tf.uint8), max_outputs=2)
tf.summary.image("pred_annotation", tf.cast(pred_annotation, tf.uint8), max_outputs=2)
loss = tf.reduce_mean((tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits,
labels=tf.squeeze(annotation, squeeze_dims=[3]),
name="entropy")))
tf.summary.scalar("entropy", loss)
trainable_var = tf.trainable_variables()
if FLAGS.debug:
for var in trainable_var:
utils.add_to_regularization_and_summary(var)
train_op = train(loss, trainable_var)
print("Setting up summary op...")
summary_op = tf.summary.merge_all()
print("Setting up image reader...")
train_records, valid_records = scene_parsing.read_dataset(FLAGS.data_dir)
print(len(train_records))
print(len(valid_records))
print("Setting up dataset reader")
image_options = {'resize': True, 'resize_size': IMAGE_SIZE}
if FLAGS.mode == 'train':
train_dataset_reader = dataset.BatchDatset(train_records, image_options)
validation_dataset_reader = dataset.BatchDatset(valid_records, image_options)
sess = tf.Session()
print("Setting up Saver...")
saver = tf.train.Saver()
summary_writer = tf.summary.FileWriter(FLAGS.logs_dir, sess.graph)
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(FLAGS.logs_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
print("Model restored...")
if FLAGS.mode == "train":
for itr in xrange(MAX_ITERATION):
train_images, train_annotations = train_dataset_reader.next_batch(FLAGS.batch_size)
feed_dict = {image: train_images, annotation: train_annotations, keep_probability: 0.85}
sess.run(train_op, feed_dict=feed_dict)
if itr % 10 == 0:
train_loss, summary_str = sess.run([loss, summary_op], feed_dict=feed_dict)
print("Step: %d, Train_loss:%g" % (itr, train_loss))
summary_writer.add_summary(summary_str, itr)
if itr % 500 == 0:
valid_images, valid_annotations = validation_dataset_reader.next_batch(FLAGS.batch_size)
valid_loss = sess.run(loss, feed_dict={image: valid_images, annotation: valid_annotations,
keep_probability: 1.0})
print("%s ---> Validation_loss: %g" % (datetime.datetime.now(), valid_loss))
saver.save(sess, FLAGS.logs_dir + "model.ckpt", itr)
elif FLAGS.mode == "visualize":
valid_images, valid_annotations = validation_dataset_reader.get_random_batch(FLAGS.batch_size)
pred = sess.run(pred_annotation, feed_dict={image: valid_images, annotation: valid_annotations,
keep_probability: 1.0})
valid_annotations = np.squeeze(valid_annotations, axis=3)
pred = np.squeeze(pred, axis=3)
for itr in range(FLAGS.batch_size):
utils.save_image(valid_images[itr].astype(np.uint8), FLAGS.logs_dir, name="inp_" + str(5+itr))
utils.save_image(valid_annotations[itr].astype(np.uint8), FLAGS.logs_dir, name="gt_" + str(5+itr))
utils.save_image(pred[itr].astype(np.uint8), FLAGS.logs_dir, name="pred_" + str(5+itr))
print("Saved image: %d" % itr)
该错误描述为： 未找到：在检查点中找不到密钥推断/ rnn1_2 / fw / basic_lstm_cell /权重
所以我认为变量一定有问题。 如果有人能告诉我如何解决它，我将非常感激！ 期待您的帮助！