我正在为我的自主直升机构建一个强化学习代理。我的纯图像输入 Keras (1.0.7) 模型如下所示:
image_model = Sequential()
image_model.add(Convolution2D(32, 8, 8, subsample=(4, 4), input_shape=(1, 120, 215)))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(64, 4, 4, subsample=(2, 2)))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(64, 3, 3, subsample=(1, 1)))
image_model.add(Activation('relu'))
image_model.add(Flatten())
image_model.add(Dense(512))
image_model.add(Activation('relu'))
image_model.add(Dense(nb_actions))
image_model.add(Activation('linear'))
为了正确学习,除了纯图像(方向、我的直升机的位置等)之外,我还必须向我的模型传递一些额外的值。我想我必须要生成一个输出层或多个输出层的网络架构流。
image_model = Sequential()
image_model.add(Convolution2D(32, 8, 8, subsample=(4, 4), input_shape=input_shape))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(64, 4, 4, subsample=(2, 2)))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(64, 3, 3, subsample=(1, 1)))
image_model.add(Activation('relu'))
image_model.add(Flatten())
image_model.add(Dense(512))
image_model.add(Activation('relu'))
value_model = Sequential()
value_model.add(Flatten(input_shape=values))
value_model.add(Dense(16))
value_model.add(Activation('relu'))
value_model.add(Dense(16))
value_model.add(Activation('relu'))
value_model.add(Dense(16))
value_model.add(Activation('relu'))
model = Sequential()
#merge together somehow
model.add(Dense(nb_actions))
model.add(Activation('linear'))
合并 API of Keras在我的理解中是为了合并图像和图像。如何将这些不同类型的输入整合在一起?
编辑:这是我对我想做的事情的尝试。我想在每个时间步用一张图像和一个单独的值训练我的代理。由于我认为我不应该将单独的值与 conv 网络流中的图像一起传递,因此我希望有第二个值流,然后最后将图像和值(value)网络结合在一起。
INPUT_SHAPE = (119, 214)
WINDOW_LENGTH = 1
img_input = (WINDOW_LENGTH,) + INPUT_SHAPE
img = Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu', input_shape=img_input)
img = Convolution2D(64, 4, 4, subsample=(2, 2), activation='relu', input_shape=img)
img = Convolution2D(64, 3, 3, subsample=(1, 1), activation='relu', input_shape=img)
img = Flatten(input_shape=img)
img = Dense(512, activation='relu', input_shape=img)
value_input = (1,2)
value = Flatten()(value_input)
value = Dense(16, activation='relu')(value)
value = Dense(16, activation='relu')(value)
value = Dense(16, activation='relu')(value)
actions = Dense(nb_actions, activation='linear')(img)(value)
model = Model([img_input, value_input], [actions])
img = Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu', input_shape=img_input) 或 img = Convolution2D(32, 8 , 8, 子样本=(4, 4), activation='relu')(img_input) 样式不起作用。
我也不知道如何在 actions = Dense(nb_actions, activation='linear')(img)(value)
请您参考如下方法:
为此,您将不得不使用模型类 API 而不是顺序 API。
不知道你想在这里实现什么,我希望下面的代码能帮助你
inp = Input((1, 120, 215))
x = Convolution2D(32, 8, 8, subsample=(4, 4), activation='relu')(inp)
x = Convolution2D(64, 4, 4, subsample=(2, 2), activation='relu')(x)
x = Convolution2D(64, 3, 3, subsample=(1, 1), activation='relu')(x)
x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x_a = Dense(nb_actions, name='a', activation='linear')(x)
x_b = Dense(nb_classes, activation='softmax', name='b')(x)
model = Model([inp], [x_a, x_b])
model.compile(Adam(lr=0.001), loss=['mse', 'categorical_crossentropy'], metrics=['accuracy'],
loss_weights=[.0001, 1.]) #adjust loss-Weights
model.fit(train_feat, [train_labels_a, train_labels_b], batch_size=batch_size, nb_epoch=3,
validation_data=(val_feat, [val_labels_a, val_labels_b]))
编辑 如果您需要 2 个输入模型和 1 个输出模型,请尝试以下操作:
from keras.models import Sequential
from keras.layers import Dense, Concatenate
image_model = Sequential()
image_model.add(Convolution2D(32, 8, 8, subsample=(4, 4), input_shape=input_shape))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(64, 4, 4, subsample=(2, 2)))
image_model.add(Activation('relu'))
image_model.add(Convolution2D(64, 3, 3, subsample=(1, 1)))
image_model.add(Activation('relu'))
image_model.add(Flatten())
image_model.add(Dense(512))
image_model.add(Activation('relu'))
value_model = Sequential()
value_model.add(Flatten(input_shape=values))
value_model.add(Dense(16))
value_model.add(Activation('relu'))
value_model.add(Dense(16))
value_model.add(Activation('relu'))
value_model.add(Dense(16))
value_model.add(Activation('relu'))
merged = Concatenate([image_model, value_model])
final_model = Sequential()
final_model.add(merged)
final_model.add(Dense(nb_actions, activation='linear'))
