[英]Classifying a numpy array image
I am using the Tensorflow for Poets tutorial to classify an image. 我正在使用Tensorflow for Poets教程对图像进行分类。 I am using the code below to classify an image, but would like to feed in a numpy array as the image instead of a jpeg, how would the code have to change?
我正在使用下面的代码对图像进行分类,但是想将numpy数组作为图像而不是jpeg进行输入,代码将如何更改?
import tensorflow as tf
import sys
# change this as you see fit
image_path = sys.argv[1]
# Read in the image_data
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line
in tf.gfile.GFile("/tf_files/retrained_labels.txt")]
# Unpersists graph from file
with tf.gfile.FastGFile("/tf_files/retrained_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')
predictions = sess.run(softmax_tensor, \
{'DecodeJpeg/contents:0': image_data})
# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]
for node_id in top_k:
human_string = label_lines[node_id]
score = predictions[0][node_id]
print('%s (score = %.5f)' % (human_string, score))
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
- If I'm not reading from a file, I imagine I don't need this. image_data = tf.gfile.FastGFile(image_path, 'rb').read()
-如果我不从文件中读取,我想我不需要这个。
predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})
- I know I don't need to override this aspect of the feed_dict, but what should I do instead? predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': image_data})
-我知道我不需要覆盖feed_dict的这一方面,但是我应该怎么做呢?
Overall, how can I make sure that a nparray I have that represents an image be used properly for prediction? 总体而言,如何确保我拥有的代表图像的nparray可以正确地用于预测?
Thank you all, I have found the answer: 谢谢大家,我找到了答案:
supposed I have a 3-dimensional numpy array with size (100,132,3) called image
. 假设我有一个大小为(100,132,3)的3维numpy数组,称为
image
。
All I have to do is pass it into the softmax classifier using 'DecodeJpeg:0
rather than DecodeJpeg/contents:0
like so... 我要做的就是使用
'DecodeJpeg:0
而不是DecodeJpeg/contents:0
这样将其传递到softmax分类器中...
predictions = sess.run(softmax_tensor, {'DecodeJpeg:0': image})
... and there you have it ...在那里
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.