CODEWITHSUNDEEP
pythonimagetensorflowclassification
Claire
Claire

Reputation: 11

tensorflow classify multiple images

I am using the Tensorflow image classification example (https://www.tensorflow.org/versions/r0.9/tutorials/image_recognition/index.html). How could I classify multiple images at a time?

EDIT: Ideally, I would just pass in one image and a number (nb) as arguments, and then make the input-to-be-classified nb iterations of that image

The file is classify_image.py, and the important portion is:

def run_inference_on_image(image):
"""Runs inference on an image.

Args:
image: Image file name.

Returns:
Nothing
"""
if not tf.gfile.Exists(image):
tf.logging.fatal('File does not exist %s', image)
image_data = tf.gfile.FastGFile(image, 'rb').read()

# Creates graph from saved GraphDef.
create_graph()

with tf.Session() as sess:
# Some useful tensors:
# 'softmax:0': A tensor containing the normalized prediction across
#   1000 labels.
# 'pool_3:0': A tensor containing the next-to-last layer containing 2048
#   float description of the image.
# 'DecodeJpeg/contents:0': A tensor containing a string providing JPEG
#   encoding of the image.
# Runs the softmax tensor by feeding the image_data as input to the graph.
softmax_tensor = sess.graph.get_tensor_by_name('softmax:0')
predictions = sess.run(softmax_tensor,
                       {'DecodeJpeg/contents:0': image_data})
predictions = np.squeeze(predictions)

# Creates node ID --> English string lookup.
node_lookup = NodeLookup()

top_k = predictions.argsort()[-FLAGS.num_top_predictions:][::-1]
for node_id in top_k:
  human_string = node_lookup.id_to_string(node_id)
  score = predictions[node_id]
  print('%s (score = %.5f)' % (human_string, score))

def main(_):
maybe_download_and_extract()
image = (FLAGS.image_file if FLAGS.image_file else
       os.path.join(FLAGS.model_dir, 'cropped_panda.jpg'))
run_inference_on_image(image)

Upvotes: 1

Views: 3020

Answers (1)

mathetes
mathetes

Reputation: 12107

The code relevant to you would be this section:

def main(_):
  maybe_download_and_extract()
  image = (FLAGS.image_file if FLAGS.image_file else
           os.path.join(FLAGS.model_dir, 'cropped_panda.jpg'))
  run_inference_on_image(image)

In order to have predictions for all the png, jpeg or jpg files in a "images" folder, you could do this:

def main(_):
  maybe_download_and_extract()

  # search for files in 'images' dir
  files_dir = os.getcwd() + '/images'
  files = os.listdir(files_dir)

  # loop over files, print prediction if it is an image
  for f in files:
    if f.lower().endswith(('.png', '.jpg', '.jpeg')):
      image_path = files_dir + '/' + f
      print run_inference_on_image(image_path)

This should print out the predictions for all your images in that folder

Upvotes: 1

Related Questions