[英]Error while using TimeDistributed with VGG19 Keras model
While using pre-trained VGG19 with with TimeDistributed in Keras, I have the following Error : 在Keras中将经过训练的VGG19与TimeDistributed一起使用时,出现以下错误:
TypeError: can only concatenate tuple (not "list") to tuple
This is in windows, Keras, python3.6 这是在Windows,Keras,python3.6中
def build_vgg(self):
img = Input(shape=(self.n_frames, self.img_rows, self.img_cols, 3))
# Get the vgg network from Keras applications
vgg = VGG19(weights="imagenet", include_top=False, input_shape=(self.img_rows, self.img_cols, 3))
# Output the first three pooling layers
outputs = [vgg.layers[i].output for i in self.vgg_layers]
vgg.outputs = outputs
# Create model and compile,
vggmodel = Model(inputs=vgg.inputs, outputs=outputs)
vggmodel.trainable = False
h2 = layers.wrappers.TimeDistributed(vggmodel)(img)
model = Model(inputs=img,outputs=h2)
model.compile(loss='mse', optimizer='adam')
return model
I am expecting the trained VGG19 model will be loaded and TimeDistributed wrapper will use the trained model and make it works in Video. 我期望将加载经过训练的VGG19模型,并且TimeDistributed包装器将使用经过训练的模型并使它在视频中工作。
The error displayed when executing this line on code: 在代码上执行此行时显示的错误:
h2 = layers.wrappers.TimeDistributed(vggmodel)(img)
i re-write it that way and it works fine 我用这种方式重写它,并且效果很好
def build_vgg(self): def build_vgg():
video = Input(shape=(self.n_frames, self.img_rows, self.img_cols, 3))
# Get the vgg network from Keras applications
vgg = VGG19(weights="imagenet", include_top=False, input_shape=(self.img_rows, self.img_cols, 3))
# Output the first three pooling layers
vgg.outputs = [vgg.layers[i].output for i in self.vgg_layers]
# Create model and compile,
vggmodel = Model(inputs=vgg.inputs, outputs=vgg.outputs)
#vggmodel.trainable = False
h2 = []
for out in vggmodel.output:
h2.append(layers.wrappers.TimeDistributed(Model(vggmodel.input,out))(video))
model = Model(inputs=video, outputs=h2)
model.trainable = False
model.compile(loss='mse', optimizer='adam')
return model
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.