我在this article之后使用 transfer learning 方法重新调整了 Inception V3
网络 .
为此,我删除了最终的网络层,并将数百张脸部图像输入网络 .
然后成功生成了一个新模型: inceptionv3-ft.model
现在我想加载这个模型并使用它的固定权重将我的面部作为'theme'应用于输入图像,如 google-dream
.
为此,我使用 keras
程序,它加载如下模型:
from keras.applications import inception_v3
# Build the InceptionV3 network with our placeholder.
# The model will be loaded with pre-trained ImageNet weights.
model = inception_v3.InceptionV3(weights='imagenet',
include_top=False)
dream = model.input
完整代码:https://github.com/keras-team/keras/blob/master/examples/deep_dream.py
So, how do I load and pass not a pre-trained but rather my RE-trained model weights?
1 回答
只是: