def vgg_net(weights, image):
layers = ('conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1',
'relu2_1', 'conv2_2', 'relu2_2', 'pool2', 'conv3_1', 'relu3_1',
'conv3_2', 'relu3_2', 'conv3_3', 'relu3_3', 'conv3_4', 'relu3_4',
'pool3', 'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
'relu4_3', 'conv4_4', 'relu4_4', 'pool4', 'conv5_1', 'relu5_1',
'conv5_2', 'relu5_2', 'conv5_3', 'relu5_3', 'conv5_4', 'relu5_4')
net = {}
current = image
for i, name in enumerate(layers):
kind = name[:4] # layer的类型,是conv还是relu或者pool.
if kind == 'conv':
kernels, bias = weights[i][0][0][0][0]
kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)),
name=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
current = utils.conv2d_basic(current, kernels, bias)
current = utils.batch_norm_layer(current,
FLAGS.mode,
scope_bn=name) # BN处理.
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
elif kind == 'pool':
# current = utils.max_pool_2x2(current)
current = utils.avg_pool_2x2(current)
net[name] = current
return net
def vgg_net(weights, image):
layers = (
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1',
'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3',
'relu3_3', 'conv3_4', 'relu3_4', 'pool3',
'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
'relu4_3', 'conv4_4', 'relu4_4', 'pool4',
'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3',
'relu5_3', 'conv5_4', 'relu5_4'
)
net = {}
current = image
for i, name in enumerate(layers):
kind = name[:4] # layer的类型,是conv还是relu或者pool.
if kind == 'conv':
kernels, bias = weights[i][0][0][0][0]
kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)), name=name + "_w")
bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
if name[4:5] == '5': # conv5开始使用atrous_conv2d卷积.
current = utils.atrous_conv2d_basic(current, kernels, bias, 2) # rate=2,也即pad=2.
current = utils.batch_norm_layer(current, FLAGS.mode, scope_bn=name) # BN处理.
else: # conv1-4
current = utils.conv2d_basic(current, kernels, bias)
current = utils.batch_norm_layer(current, FLAGS.mode, scope_bn=name) # BN处理.
elif kind == 'relu':
current = tf.nn.relu(current, name=name)
if FLAGS.debug:
utils.add_activation_summary(current)
elif kind == 'pool':
if name[4:5] == '4':
current = utils.max_pool_1x1(current)
else:
current = utils.max_pool_3x3(current)
net[name] = current
return net
def inference(image, keep_prob, mean): # keep_prob为dropout的占位符.
print("setting up vgg initialized conv layers ...")
model_data = utils.get_model_data(FLAGS.model_dir,
MODEL_URL) # 下载得到VGGmodel
mean_pixel = mean
weights = np.squeeze(model_data['layers'])
processed_image = utils.process_image(image, mean_pixel) # 图像像素值-平均像素值
with tf.variable_scope("inference"):
image_net = vgg_net(weights, processed_image)
conv_final_layer = image_net["conv5_4"]
pool5 = utils.max_pool_1x1(conv_final_layer)
# w6~w8都可以做正则化的把?因为都是全连接层啊.
# 7x7改成3x3，4096改成了1024，可能特征不够？
# 新加的w6-w8 b6-b8都自带初始化.
W6 = utils.weight_variable([3, 3, 512, 512], name="W6")
b6 = utils.bias_variable([512], name="b6")
# data_format = "channels_last" 为默认
# 使用不同rate的孔卷积.
Fc6_1 = utils.atrous_conv2d_basic(pool5, W6, b6, 6)
Fc6_2 = utils.atrous_conv2d_basic(pool5, W6, b6, 12)
Fc6_3 = utils.atrous_conv2d_basic(pool5, W6, b6, 18)
Fc6_4 = utils.atrous_conv2d_basic(pool5, W6, b6, 24)
Bn6_1 = utils.batch_norm_layer(Fc6_1, FLAGS.mode,
scope_bn='Bn') # bn处理要在relu之前.
Bn6_2 = utils.batch_norm_layer(Fc6_2, FLAGS.mode, scope_bn='Bn')
Bn6_3 = utils.batch_norm_layer(Fc6_3, FLAGS.mode, scope_bn='Bn')
Bn6_4 = utils.batch_norm_layer(Fc6_4, FLAGS.mode, scope_bn='Bn')
relu6_1 = tf.nn.relu(Bn6_1, name="relu6_1")
relu6_2 = tf.nn.relu(Bn6_2, name="relu6_2")
relu6_3 = tf.nn.relu(Bn6_3, name="relu6_3")
relu6_4 = tf.nn.relu(Bn6_4, name="relu6_4")
relu_dropout6_1 = tf.nn.dropout(relu6_1, keep_prob=keep_prob)
relu_dropout6_2 = tf.nn.dropout(relu6_2, keep_prob=keep_prob)
relu_dropout6_3 = tf.nn.dropout(relu6_3, keep_prob=keep_prob)
relu_dropout6_4 = tf.nn.dropout(relu6_4, keep_prob=keep_prob)
W7 = utils.weight_variable([1, 1, 512, 512], name="W7")
b7 = utils.bias_variable([512], name="b7")
Fc7_1 = utils.conv2d_basic(relu_dropout6_1, W7, b7)
Fc7_2 = utils.conv2d_basic(relu_dropout6_2, W7, b7)
Fc7_3 = utils.conv2d_basic(relu_dropout6_3, W7, b7)
Fc7_4 = utils.conv2d_basic(relu_dropout6_4, W7, b7)
Bn7_1 = utils.batch_norm_layer(Fc7_1, FLAGS.mode, scope_bn='Bn')
Bn7_2 = utils.batch_norm_layer(Fc7_2, FLAGS.mode, scope_bn='Bn')
Bn7_3 = utils.batch_norm_layer(Fc7_3, FLAGS.mode, scope_bn='Bn')
Bn7_4 = utils.batch_norm_layer(Fc7_4, FLAGS.mode, scope_bn='Bn')
relu7_1 = tf.nn.relu(Bn7_1, name="relu7_1")
relu7_2 = tf.nn.relu(Bn7_2, name="relu7_2")
relu7_3 = tf.nn.relu(Bn7_3, name="relu7_3")
relu7_4 = tf.nn.relu(Bn7_4, name="relu7_4")
relu_dropout7_1 = tf.nn.dropout(relu7_1, keep_prob=keep_prob)
relu_dropout7_2 = tf.nn.dropout(relu7_2, keep_prob=keep_prob)
relu_dropout7_3 = tf.nn.dropout(relu7_3, keep_prob=keep_prob)
relu_dropout7_4 = tf.nn.dropout(relu7_4, keep_prob=keep_prob)
W8 = utils.weight_variable([1, 1, 512, NUM_OF_CLASSESS], name="W8")
b8 = utils.bias_variable([NUM_OF_CLASSESS], name="b8")
Fc8_1 = utils.conv2d_basic(relu_dropout7_1, W8, b8)
Fc8_2 = utils.conv2d_basic(relu_dropout7_2, W8, b8)
Fc8_3 = utils.conv2d_basic(relu_dropout7_3, W8, b8)
Fc8_4 = utils.conv2d_basic(relu_dropout7_4, W8, b8)
Fc8 = tf.add_n([Fc8_1, Fc8_2, Fc8_3, Fc8_4],
name="Fc8") # F8的各个层尺寸一样,感受野不同.
shape = tf.shape(image)
resize_Fc8 = tf.image.resize_images(
Fc8,
(shape[1],
shape[2])) # tf自带的扩尺寸函数resize_images(),默认双线性插值.尺寸扩大8倍至原尺寸256x256
softmax = tf.nn.softmax(resize_Fc8) # tf.nn.softmax(),使前向计算结果转为概率分布
annotation_pred = tf.argmax(softmax, dimension=3, name="prediction")
return tf.expand_dims(annotation_pred, dim=3), resize_Fc8, softmax
