本文整理汇总了Python中vgg16.VGG16属性的典型用法代码示例。如果您正苦于以下问题：Python vgg16.VGG16属性的具体用法？Python vgg16.VGG16怎么用？Python vgg16.VGG16使用的例子？那么, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类vgg16的用法示例。
在下文中一共展示了vgg16.VGG16属性的6个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: load_encoding_model
# 需要导入模块: import vgg16 [as 别名]
# 或者: from vgg16 import VGG16 [as 别名]
def load_encoding_model():
model = VGG16(weights='imagenet', include_top=True, input_shape = (224, 224, 3))
return model 示例2: create_model
# 需要导入模块: import vgg16 [as 别名]
# 或者: from vgg16 import VGG16 [as 别名]
def create_model(self, ret_model = False):
#base_model = VGG16(weights='imagenet', include_top=False, input_shape = (224, 224, 3))
#base_model.trainable=False
image_model = Sequential()
#image_model.add(base_model)
#image_model.add(Flatten())
image_model.add(Dense(EMBEDDING_DIM, input_dim = 4096, activation='relu'))
image_model.add(RepeatVector(self.max_cap_len))
lang_model = Sequential()
lang_model.add(Embedding(self.vocab_size, 256, input_length=self.max_cap_len))
lang_model.add(LSTM(256,return_sequences=True))
lang_model.add(TimeDistributed(Dense(EMBEDDING_DIM)))
model = Sequential()
model.add(Merge([image_model, lang_model], mode='concat'))
model.add(LSTM(1000,return_sequences=False))
model.add(Dense(self.vocab_size))
model.add(Activation('softmax'))
print "Model created!"
if(ret_model==True):
return model
model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
return model 示例3: run
# 需要导入模块: import vgg16 [as 别名]
# 或者: from vgg16 import VGG16 [as 别名]
def run(self):
global label
# Load the VGG16 network
print("[INFO] loading network...")
self.model = VGG16(weights="imagenet")
while (~(frame is None)):
(inID, label) = self.predict(frame) 示例4: __init__
# 需要导入模块: import vgg16 [as 别名]
# 或者: from vgg16 import VGG16 [as 别名]
def __init__(self):
super(RPN, self).__init__()
self.features = VGG16(bn=False)
self.conv1 = Conv2d(512, 512, 3, same_padding=True)
self.score_conv = Conv2d(512, len(self.anchor_scales) * 3 * 2, 1, relu=False, same_padding=False)
self.bbox_conv = Conv2d(512, len(self.anchor_scales) * 3 * 4, 1, relu=False, same_padding=False)
# loss
self.cross_entropy = None
self.los_box = None 示例5: model_gen
# 需要导入模块: import vgg16 [as 别名]
# 或者: from vgg16 import VGG16 [as 别名]
def model_gen():
model = VGG16(weights='imagenet', include_top=True, input_shape = (224, 224, 3))
return model 示例6: encode_image
# 需要导入模块: import vgg16 [as 别名]
# 或者: from vgg16 import VGG16 [as 别名]
def encode_image():
model = VGG16(weights='imagenet', include_top=True, input_shape = (224, 224, 3))
image_encodings = {}
train_imgs_id = open("Flickr8K_Text/Flickr_8k.trainImages.txt").read().split('\n')[:-1]
print len(train_imgs_id)
test_imgs_id = open("Flickr8K_Text/Flickr_8k.testImages.txt").read().split('\n')[:-1]
images = []
images.extend(train_imgs_id)
images.extend(test_imgs_id)
print len(images)
bar = progressbar.ProgressBar(maxval=len(images), \
widgets=[progressbar.Bar('=', '[', ']'), ' ', progressbar.Percentage()])
bar.start()
counter=1
print "Encoding images"
for img in images:
path = "Flickr8K_Data/"+str(img)
image_encodings[img] = encodings(model, path)
bar.update(counter)
counter += 1
bar.finish()
with open( "image_encodings.p", "wb" ) as pickle_f:
pickle.dump( image_encodings, pickle_f )
print "Encodings dumped into image_encodings.p"