CODEWITHSUNDEEP
pythontensorflowbazel
Aggounix
Aggounix

Reputation: 251

Tensorflow inception without bazel

I tried this image recognition tutorial from tensorflow site: https://www.tensorflow.org/tutorials/image_retraining and it worked succefully with bazel bu command line Is it possible to call this inception model programmatically using bazel or by a python script for example so I can feed it with images easily

Upvotes: 0

Views: 376

Answers (1)

user6083088
user6083088

Reputation: 1037

You can use the generated files under tmp directory and write a python script to load the model and generate predictions.

Also, it is advisable to keep the files in a directory other than tmp folder as the contents of the folders can be flushed away.

import tensorflow as tf
import sys


image_path = sys.argv[1]
image_data = tf.gfile.FastGFile(image_path, 'rb').read()

#loads label file, strips off carriage return
label_lines = [line.strip() for line in tf.gfile.GFile("/tmp/output_labels.txt")]

# Unpersists graph from file
with tf.gfile.FastGFile("/tmp/output_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 an 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 = %.2f)' % (human_string, score))

Upvotes: 1

Related Questions