在读取图像文件并对其进行规范化之后，我想知道在开始时哪个节点将作为输入。
我使用此函数（来自tensorflow存储库）
对图像进行了规范化def read_tensor_from_image_file(file_name, input_height=299, input_width=299,
input_mean=0, input_std=255):
input_name = "file_reader"
output_name = "normalized"
file_reader = tf.read_file(file_name, input_name)
if file_name.endswith(".png"):
image_reader = tf.image.decode_png(file_reader, channels = 3,
name='png_reader')
elif file_name.endswith(".gif"):
image_reader = tf.squeeze(tf.image.decode_gif(file_reader,
name='gif_reader'))
elif file_name.endswith(".bmp"):
image_reader = tf.image.decode_bmp(file_reader, name='bmp_reader')
else:
image_reader = tf.image.decode_jpeg(file_reader, channels = 3,
name='jpeg_reader')
float_caster = tf.cast(image_reader, tf.float32)
dims_expander = tf.expand_dims(float_caster, 0);
resized = tf.image.resize_bilinear(dims_expander, [input_height, input_width])
normalized = tf.divide(tf.subtract(resized, [input_mean]), [input_std])
sess = tf.Session()
result = sess.run(normalized)
return result
查看初始操作：
<bound method Operation.values of <tf.Operation 'import/DecodeJpeg/contents' type=Const>>
<bound method Operation.values of <tf.Operation 'import/DecodeJpeg' type=DecodeJpeg>>
<bound method Operation.values of <tf.Operation 'import/Cast' type=Cast>>
<bound method Operation.values of <tf.Operation 'import/ExpandDims/dim' type=Const>>
<bound method Operation.values of <tf.Operation 'import/ExpandDims' type=ExpandDims>>
<bound method Operation.values of <tf.Operation 'import/ResizeBilinear/size' type=Const>>
<bound method Operation.values of <tf.Operation 'import/ResizeBilinear' type=ResizeBilinear>>
<bound method Operation.values of <tf.Operation 'import/Sub/y' type=Const>>
<bound method Operation.values of <tf.Operation 'import/Sub' type=Sub>>
<bound method Operation.values of <tf.Operation 'import/Mul/y' type=Const>>
<bound method Operation.values of <tf.Operation 'import/Mul' type=Mul>>
<bound method Operation.values of <tf.Operation 'import/conv/conv2d_params' type=Const>>
似乎前几层对jpeg文件进行了规范化，由于上面提供的功能，我可以跳过它。
现在我不确定我可以输入result的位置（上述功能的结果）：
我不确定Mul（乘法）在这种情况下做了什么，但我假设该节点的操作结果应该与结果相同我上面的功能？我的假设是基于后续层 - 这是一个围绕参数（权重？）
所以我想知道我是否可以将其作为输入用于推理。
谢谢。
编辑：这些是来自tf存储库的脚本我使用：
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/label_image/label_image.py