qq_28057379的博客

1、ckpt转pbimport tensorflow as tfdef freeze_graph(input_checkpoint, output_graph): # 指定输出的节点名称,该节点名称必须是原模型中存在的节点(重要！！！！！！！！！，如何找到该节点名称，见下文) output_node_names = ['attn_cell_1/transpose_1'] saver = tf.train.import_meta_graph(input_checkpoint + '

1、Numpy转TensorTensorFlow 通过 convert_to_tensor() 函数将Numpy转换为Tensor，代码如下：import tensorflow as tfimport numpy as np# 创建ndarrayarray = np.array([1, 2, 3, 4, 5], np.float32)print(array) #[1. 2. 3. 4. 5.]# 将ndarray转化为tensort = tf.convert_to_tensor(array,