"""
There are 32 different Mobilenet models to choose from, with a variety of file
size and latency options. The first number can be '1.0', '0.75', '0.50', or
'0.25' to control the size, and the second controls the input image size, either
'224', '192', '160', or '128', with smaller sizes running faster. See
https://research.googleblog.com/2017/06/mobilenets-open-source-models-for.html
for more information on Mobilenet.
To use with TensorBoard:
By default, this script will log summaries to /tmp/retrain_logs directory
Visualize the summaries with this command:
tensorboard --logdir /tmp/retrain_logs
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import collections
from datetime import datetime
import hashlib
import os
import os.path
import random
import re
import sys
import tarfile
import numpy as np
from six.moves import urllib
import tensorflow as tf
from tensorflow.python.framework import graph_util
from tensorflow.python.framework import tensor_shape
from tensorflow.python.platform import gfile
from tensorflow.python.util import compat
from bean.ml_config import MLConfig
from bean.audio_sample import AudioSample, parseLabelConfig
from util.parser import AudioParser
# These are all parameters that are tied to the particular model architecture
# we're using for Inception v3. These include things like tensor names and their
# sizes. If you want to adapt this script to work with another model, you will
# need to update these to reflect the values in the network you're using.
MAX_NUM_IMAGES_PER_CLASS = 2**27 - 1 # ~134M
def create_image_lists(image_dir, testing_percentage, validation_percentage):
if not gfile.Exists(image_dir):
tf.logging.error("Image directory '" + image_dir + "' not found.")
return None
result = collections.OrderedDict()
sub_dirs = [
os.path.join(image_dir, item)
for item in gfile.ListDirectory(image_dir)
]
sub_dirs = sorted(item for item in sub_dirs if gfile.IsDirectory(item))
for sub_dir in sub_dirs:
extensions = ['jpg', 'jpeg', 'JPG', 'JPEG']
file_list = []
dir_name = os.path.basename(sub_dir)
if dir_name == image_dir:
continue
tf.logging.info("Looking for images in '" + dir_name + "'")
for extension in extensions:
file_glob = os.path.join(image_dir, dir_name, '*.' + extension)
file_list.extend(gfile.Glob(file_glob))
if not file_list:
tf.logging.warning('No files found')
continue
if len(file_list) < 20:
tf.logging.warning(
'WARNING: Folder has less than 20 images, which may cause issues.'
)
elif len(file_list) > MAX_NUM_IMAGES_PER_CLASS:
tf.logging.warning(
'WARNING: Folder {} has more than {} images. Some images will '
'never be selected.'.format(dir_name,
MAX_NUM_IMAGES_PER_CLASS))
label_name = re.sub(r'[^a-z0-9]+', ' ', dir_name.lower())
training_images = []
testing_images = []
validation_images = []
for file_name in file_list:
base_name = os.path.basename(file_name)
# We want to ignore anything after '_nohash_' in the file name when
# deciding which set to put an image in, the data set creator has a way of
# grouping photos that are close variations of each other. For example
# this is used in the plant disease data set to group multiple pictures of
# the same leaf.
hash_name = re.sub(r'_nohash_.*$', '', file_name)
# This looks a bit magical, but we need to decide whether this file should
# go into the training, testing, or validation sets, and we want to keep
# existing files in the same set even if more files are subsequently
# added.
# To do that, we need a stable way of deciding based on just the file name
# itself, so we do a hash of that and then use that to generate a
# probability value that we use to assign it.
hash_name_hashed = hashlib.sha1(
compat.as_bytes(hash_name)).hexdigest()
percentage_hash = (
(int(hash_name_hashed, 16) % (MAX_NUM_IMAGES_PER_CLASS + 1)) *
(100.0 / MAX_NUM_IMAGES_PER_CLASS))
if percentage_hash < validation_percentage:
validation_images.append(base_name)
elif percentage_hash < (
testing_percentage + validation_percentage):
testing_images.append(base_name)
else:
training_images.append(base_name)
result[label_name] = {
'dir': dir_name,
'training': training_images,
'testing': testing_images,
'validation': validation_images,
}
return result
def get_image_path(image_lists, label_name, index, image_dir, category):
if label_name not in image_lists:
tf.logging.fatal('Label does not exist %s.', label_name)
label_lists = image_lists[label_name]
if category not in label_lists:
tf.logging.fatal('Category does not exist %s.', category)
category_list = label_lists[category]
if not category_list:
tf.logging.fatal('Label %s has no images in the category %s.',
label_name, category)
mod_index = index % len(category_list)
base_name = category_list[mod_index]
sub_dir = label_lists['dir']
full_path = os.path.join(image_dir, sub_dir, base_name)
return full_path
def get_bottleneck_path(image_lists, label_name, index, bottleneck_dir,
category, architecture):
return get_image_path(image_lists, label_name, index, bottleneck_dir,
category) + '_' + architecture + '.txt'
def create_model_graph(model_info, config):
with tf.Graph().as_default() as graph:
model_path = os.path.join(config['model_dir'],
model_info['model_file_name'])
with gfile.FastGFile(model_path, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
bottleneck_tensor, resized_input_tensor = (tf.import_graph_def(
graph_def,
name='',
return_elements=[
model_info['bottleneck_tensor_name'],
model_info['resized_input_tensor_name'],
]))
return graph, bottleneck_tensor, resized_input_tensor
def run_bottleneck_on_image(sess, image_data, image_data_tensor,
decoded_image_tensor, resized_input_tensor,
bottleneck_tensor):
# First decode the JPEG image, resize it, and rescale the pixel values.
resized_input_values = sess.run(decoded_image_tensor,
{image_data_tensor: image_data})
# Then run it through the recognition network.
bottleneck_values = sess.run(bottleneck_tensor,
{resized_input_tensor: resized_input_values})
bottleneck_values = np.squeeze(bottleneck_values)
return bottleneck_values
def maybe_download_and_extract(config, data_url):
dest_directory = config['model_dir']
if not os.path.exists(dest_directory):
os.makedirs(dest_directory)
filename = data_url.split('/')[-1]
filepath = os.path.join(dest_directory, filename)
if not os.path.exists(filepath):
def _progress(count, block_size, total_size):
sys.stdout.write(
'\r>> Downloading %s %.1f%%' %
(filename,
float(count * block_size) / float(total_size) * 100.0))
sys.stdout.flush()
filepath, _ = urllib.request.urlretrieve(data_url, filepath, _progress)
statinfo = os.stat(filepath)
tf.logging.info('Successfully downloaded', filename, statinfo.st_size,
'bytes.')
tarfile.open(filepath, 'r:gz').extractall(dest_directory)
def ensure_dir_exists(dir_name):
"""Makes sure the folder exists on disk.
Args:
dir_name: Path string to the folder we want to create.
"""
if not os.path.exists(dir_name):
os.makedirs(dir_name)
bottleneck_path_2_bottleneck_values = {}
def create_bottleneck_file(bottleneck_path, image_lists, label_name, index,
image_dir, category, sess, jpeg_data_tensor,
decoded_image_tensor, resized_input_tensor,
bottleneck_tensor):
"""Create a single bottleneck file."""
tf.logging.info('Creating bottleneck at ' + bottleneck_path)
image_path = get_image_path(image_lists, label_name, index, image_dir,
category)
if not gfile.Exists(image_path):
tf.logging.fatal('File does not exist %s', image_path)
image_data = gfile.FastGFile(image_path, 'rb').read()
try:
bottleneck_values = run_bo