def build(self,
weights_path="open_nsfw-weights.npy",
input_type=InputType.TENSOR):
self.weights = np.load(weights_path, encoding="latin1").item()
self.input_tensor = None
if input_type == InputType.TENSOR:
self.input = tf.placeholder(
tf.float32, shape=[None, 224, 224, 3], name="input")
self.input_tensor = self.input
elif input_type == InputType.BASE64_JPEG:
from image_utils import load_base64_tensor
self.input = tf.placeholder(
tf.string, shape=(None, ), name="input")
self.input_tensor = load_base64_tensor(self.input)
else:
raise ValueError("invalid input type '{}'".format(input_type))
x = self.input_tensor
x = tf.pad(x, [[0, 0], [3, 3], [3, 3], [0, 0]], 'CONSTANT')
x = self.__conv2d(
"conv_1",
x,
filter_depth=64,
kernel_size=7,
stride=2,
padding='valid')
x = self.__batch_norm("bn_1", x)
x = tf.nn.relu(x)
x = tf.layers.max_pooling2d(x, pool_size=3, strides=2, padding='same')
x = self.__conv_block(
stage=0,
block=0,
inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3,
stride=1)
x = self.__identity_block(
stage=0,
block=1,
inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3)
x = self.__identity_block(
stage=0,
block=2,
inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3)
x = self.__conv_block(
stage=1,
block=0,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3,
stride=2)
x = self.__identity_block(
stage=1,
block=1,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3)
x = self.__identity_block(
stage=1,
block=2,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3)
x = self.__identity_block(
stage=1,
block=3,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3)
x = self.__conv_block(
stage=2,
block=0,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3,
stride=2)
x = self.__identity_block(
stage=2,
block=1,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(
stage=2,
block=2,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(
stage=2,
block=3,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(
stage=2,
block=4,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(
stage=2,
block=5,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__conv_block(
stage=3,
block=0,
inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3,
stride=2)
x = self.__identity_block(
stage=3,
block=1,
inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = self.__identity_block(
stage=3,
block=2,
inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = tf.layers.average_pooling2d(
x, pool_size=7, strides=1, padding="valid", name="pool")
x = tf.reshape(x, shape=(-1, 1024))
self.logits = self.__fully_connected(
name="fc_nsfw", inputs=x, num_outputs=2)
self.predictions = tf.nn.softmax(self.logits, name="predictions")
def build(self, input_type=InputType.TENSOR):
#self.weights = np.load(weights_path, encoding="latin1").item()
self.input_tensor = None
self.training = tf.placeholder(tf.bool, name='training_mode')
self.learning_rate = tf.placeholder(tf.float32, name='learning_rate')
if input_type == InputType.TENSOR:
self.input = tf.placeholder(tf.float32,
shape=[None, 224, 224, 3],
name="input")
self.input_tensor = self.input
elif input_type == InputType.BASE64_JPEG:
from image_utils import load_base64_tensor
self.input = tf.placeholder(tf.string,
shape=(None, ),
name="input")
self.input_tensor = load_base64_tensor(self.input)
else:
raise ValueError("invalid input type '{}'".format(input_type))
x = self.input_tensor
self.y = tf.placeholder(tf.int32, (None))
one_hot_y = tf.one_hot(self.y, self.num_classes)
x = tf.pad(x, [[0, 0], [3, 3], [3, 3], [0, 0]], 'CONSTANT')
x = self.__conv2d("conv_1",
x,
filter_depth=64,
kernel_size=7,
stride=2,
padding='valid')
x = self.__batch_norm("bn_1", x)
x = tf.nn.relu(x)
x = tf.layers.max_pooling2d(x, pool_size=3, strides=2, padding='same')
x = self.__conv_block(stage=0,
block=0,
inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3,
stride=1)
x = self.__identity_block(stage=0,
block=1,
inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3)
x = self.__identity_block(stage=0,
block=2,
inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3)
x = self.__conv_block(stage=1,
block=0,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3,
stride=2)
x = self.__identity_block(stage=1,
block=1,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3)
x = self.__identity_block(stage=1,
block=2,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3)
x = self.__identity_block(stage=1,
block=3,
inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3)
x = self.__conv_block(stage=2,
block=0,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3,
stride=2)
x = self.__identity_block(stage=2,
block=1,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(stage=2,
block=2,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(stage=2,
block=3,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(stage=2,
block=4,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__identity_block(stage=2,
block=5,
inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3)
x = self.__conv_block(stage=3,
block=0,
inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3,
stride=2)
x = self.__identity_block(stage=3,
block=1,
inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = self.__identity_block(stage=3,
block=2,
inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = tf.layers.average_pooling2d(x,
pool_size=7,
strides=1,
padding="valid",
name="pool")
x = tf.reshape(x, shape=(-1, 1024), name='nsfw_features')
# output
self.logits = self.__fully_connected(name="fc_nsfw",
inputs=x,
num_outputs=self.num_classes)
self.loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(labels=one_hot_y,
logits=self.logits))
self.optimizer = tf.train.AdamOptimizer(
learning_rate=self.learning_rate).minimize(self.loss)
## accuracy
self.correct_prediction = tf.equal(
tf.cast(tf.argmax(self.logits, 1), tf.int32), self.y)
self.accuracy_operation = tf.reduce_mean(
tf.cast(self.correct_prediction, tf.float32))
## recall
toxic_predicts = tf.equal(tf.cast(tf.argmax(self.logits, 1), tf.int32),
tf.cast(2, tf.int32))
toxic_labels = tf.equal(self.y, tf.cast(2, tf.int32))
self.toxic_recall = tf.metrics.recall(toxic_labels, toxic_predicts)
self.toxic_label_sum = tf.reduce_sum(tf.cast(toxic_labels, tf.int32))
## precision
self.toxic_precision = tf.metrics.precision(toxic_labels,
toxic_predicts)
self.toxic_predict_sum = tf.reduce_sum(
tf.cast(toxic_predicts, tf.int32))
def build(self, weights_path="open_nsfw-weights.npy",
input_type=InputType.TENSOR):
self.weights = np.load(weights_path, encoding="latin1").item()
self.input_tensor = None
if input_type == InputType.TENSOR:
self.input = tf.placeholder(tf.float32,
shape=[None, 224, 224, 3],
name="input")
self.input_tensor = self.input
elif input_type == InputType.BASE64_JPEG:
from image_utils import load_base64_tensor
self.input = tf.placeholder(tf.string, shape=(None,), name="input")
self.input_tensor = load_base64_tensor(self.input)
else:
raise ValueError("invalid input type '{}'".format(input_type))
x = self.input_tensor
x = tf.pad(x, [[0, 0], [3, 3], [3, 3], [0, 0]], 'CONSTANT')
x = self.__conv2d("conv_1", x, filter_depth=64,
kernel_size=7, stride=2, padding='valid')
x = self.__batch_norm("bn_1", x)
x = tf.nn.relu(x)
x = tf.layers.max_pooling2d(x, pool_size=3, strides=2, padding='same')
x = self.__conv_block(stage=0, block=0, inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3, stride=1)
x = self.__identity_block(stage=0, block=1, inputs=x,
filter_depths=[32, 32, 128], kernel_size=3)
x = self.__identity_block(stage=0, block=2, inputs=x,
filter_depths=[32, 32, 128], kernel_size=3)
x = self.__conv_block(stage=1, block=0, inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3, stride=2)
x = self.__identity_block(stage=1, block=1, inputs=x,
filter_depths=[64, 64, 256], kernel_size=3)
x = self.__identity_block(stage=1, block=2, inputs=x,
filter_depths=[64, 64, 256], kernel_size=3)
x = self.__identity_block(stage=1, block=3, inputs=x,
filter_depths=[64, 64, 256], kernel_size=3)
x = self.__conv_block(stage=2, block=0, inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3, stride=2)
x = self.__identity_block(stage=2, block=1, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=2, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=3, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=4, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=5, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__conv_block(stage=3, block=0, inputs=x,
filter_depths=[256, 256, 1024], kernel_size=3,
stride=2)
x = self.__identity_block(stage=3, block=1, inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = self.__identity_block(stage=3, block=2, inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = tf.layers.average_pooling2d(x, pool_size=7, strides=1,
padding="valid", name="pool")
x = tf.reshape(x, shape=(-1, 1024))
self.logits = self.__fully_connected(name="fc_nsfw",
inputs=x, num_outputs=2)
self.predictions = tf.nn.softmax(self.logits, name="predictions")