keras分佈式模型和數據

Question

假設我有一個keras模型和函數train_model(data)來訓練它的一些數據。

我想知道是否可以合併/合併相同的體系結構，相同的hyperparam模型，這些模型是經過分別/獨立訓練的？

python train_model(data1) ### one one epoch 
python train_model(data2) ### one one epoch 
... 

然後

load(model1) 
load(model2) 
model3 = combine(model1, model2) 
### model3 equivalent to 2 epochs of learning. 

我試圖瞭解/找到一種方法來分發學習。

Answer 1

你已經試過了嗎？

from keras.models import load_model 

# load models - it is just the architecture 
model1 = load_model('path/to/trained/model1.h5') 
model2 = load_model('path/to/trained/model2.h5') 

# load trained weights 
model1.load_weights('path/to/weights/from/model1.hdf5') 
model2.load_weights('path/to/weights/from/model2.hdf5') 

# create a model that will merge both 1 and 2 
model = Sequential() 
model.add(Merge([model1, model2], mode = 'concat')) 
model.add(Dense(1)) # for regression, use you last Dense layer here 
model.compile(#your compiling parameters) 

# use your merged model 
model.predict(dataset_to_be_predicted) 

的想法是從here