xiaoyuycr/rl

reinforcement learning

rl's Issues

报错无'conv2d_8'层

cnn_model = Model(inputs=actor_model.layers[0].input,
outputs = (actor_model.get_layer('conv2d_8').output))

features = cnn_model.predict(X_train)
报错如下：
ValueError Traceback (most recent call last)
in <cell line: 1>()
1 cnn_model = Model(inputs=actor_model.layers[0].input,
----> 2 outputs = (actor_model.get_layer('conv2d_8').output))
3
4 features = cnn_model.predict(X_train)

/usr/local/lib/python3.10/dist-packages/keras/engine/training.py in get_layer(self, name, index)
3288 if layer.name == name:
3289 return layer
-> 3290 raise ValueError(
3291 f"No such layer: {name}. Existing layers are: "
3292 f"{list(layer.name for layer in self.layers)}."

ValueError: No such layer: conv2d_8. Existing layers are: ['image_inputs', 'conv2d', 'conv2d_1', 'conv2d_2', 'conv2d_3', 'flatten', 'dense', 'actions_input', 'q_outputs', 'multiply', 'q_value'].

请问怎么使用大数据？

如题，当数据很多，或者图片很大的时候 应该怎么办？

你好，请问作者的keras和TensorFlow是哪个版本的

ValueError

ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 2 dimensions. The detected shape was (64, 5) + inhomogeneous part.