tensorflow权重初始化

一，用10层神经网络，每一层的参数都是随机正态分布，均值为0，标准差为0.01 #10层神经网络 data = tf.constant(np.random.randn(2000, 800).astype('float32')) layer_sizes = [800 - 50 * i for i in range(0, 10)] num_layers = len(layer_sizes) fcs

>>阅读原文<<