我想设置一个Convolution2D图层的权重:
conv = Convolution2D(conv_out_size, window_size, embedding_size,
border_mode='same',
activation='relu',
weights=weights,
name='conv_{:d}'.format(i))(in_x)
Run Code Online (Sandbox Code Playgroud)
但我不确定这里的预期.我尝试了几件事,但大多数时候我都会尝试
ValueError: You called `set_weights(weights)` on layer "conv_0" with a weight list of length 1, but the layer was expecting 2 weights.
Run Code Online (Sandbox Code Playgroud)
不确定这究竟意味着什么.
keras ×1