I'm trying to run a trained roboflow model using my webcam on visual code studio. The webcam does load up alongside the popup, but it's just a tiny rectangle in the corner and you can't see anything else. If i change "image", image to "image",1 or something else in the cv2.imshow line, the webcam lights up for a second and returns the error code:
cv2.error: OpenCV(4.5.4) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cv::cvtColor'
Here is my code as obtained from a github roboflow has:
# load config
import json
with open('roboflow_config.json') as f:
config = json.load(f)
ROBOFLOW_API_KEY = "********"
ROBOFLOW_MODEL = "penguins-ojf2k"
ROBOFLOW_SIZE = "416"
FRAMERATE = config["FRAMERATE"]
BUFFER = config["BUFFER"]
import asyncio
import cv2
import base64
import numpy as np
import httpx
import time
# Construct the Roboflow Infer URL
# (if running locally replace https://detect.roboflow.com/ with eg http://127.0.0.1:9001/)
upload_url = "".join([
"https://detect.roboflow.com/",
ROBOFLOW_MODEL,
"?api_key=",
ROBOFLOW_API_KEY,
"&format=image", # Change to json if you want the prediction boxes, not the visualization
"&stroke=5"
])
# Get webcam interface via opencv-python
video = cv2.VideoCapture(0,cv2.CAP_DSHOW)
# Infer via the Roboflow Infer API and return the result
# Takes an httpx.AsyncClient as a parameter
async def infer(requests):
# Get the current image from the webcam
ret, img = video.read()
# Resize (while maintaining the aspect ratio) to improve speed and save bandwidth
height, width, channels = img.shape
scale = min(height, width)
img = cv2.resize(img, (2000, 1500))
# Encode image to base64 string
retval, buffer = cv2.imencode('.jpg', img)
img_str = base64.b64encode(buffer)
# Get prediction from Roboflow Infer API
resp = await requests.post(upload_url, data=img_str, headers={
"Content-Type": "application/x-www-form-urlencoded"
})
# Parse result image
image = np.asarray(bytearray(resp.content), dtype="uint8")
image = cv2.imdecode(image, cv2.IMREAD_COLOR)
return image
# Main loop; infers at FRAMERATE frames per second until you press "q"
async def main():
# Initialize
last_frame = time.time()
# Initialize a buffer of images
futures = []
async with httpx.AsyncClient() as requests:
while True:
# On "q" keypress, exit
if(cv2.waitKey(1) == ord('q')):
break
# Throttle to FRAMERATE fps and print actual frames per second achieved
elapsed = time.time() - last_frame
await asyncio.sleep(max(0, 1/FRAMERATE - elapsed))
print((1/(time.time()-last_frame)), " fps")
last_frame = time.time()
# Enqueue the inference request and safe it to our buffer
task = asyncio.create_task(infer(requests))
futures.append(task)
# Wait until our buffer is big enough before we start displaying results
if len(futures) < BUFFER * FRAMERATE:
continue
# Remove the first image from our buffer
# wait for it to finish loading (if necessary)
image = await futures.pop(0)
# And display the inference results
img = cv2.imread('img.jpg')
cv2.imshow('image', image)
# Run our main loop
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
asyncio.run(main())
# Release resources when finished
video.release()
cv2.destroyAllWindows()
It looks like you're missing your model's version number so the API is probably returning a 404 error which OpenCV is trying to read as an image.
I found your project on Roboflow Universe based on the ROBOFLOW_MODEL in your code; it looks like you're looking for version 3.
So try changing the line
ROBOFLOW_MODEL = "penguins-ojf2k"
to
ROBOFLOW_MODEL = "penguins-ojf2k/3"
It also looks like your model was trained at 640x640 (not 416x416) so you should change ROBOFLOW_SIZE to 640 as well for best results.
I have a custom dataset, that I then stored as tfrecord, doing
# toy example data
label = np.asarray([[1,2,3],
[4,5,6]]).reshape(2, 3, -1)
sample = np.stack((label + 200).reshape(2, 3, -1))
def bytes_feature(values):
"""Returns a TF-Feature of bytes.
Args:
values: A string.
Returns:
A TF-Feature.
"""
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[values]))
def labeled_image_to_tfexample(sample_binary_string, label_binary_string):
return tf.train.Example(features=tf.train.Features(feature={
'sample/image': bytes_feature(sample_binary_string),
'sample/label': bytes_feature(label_binary_string)
}))
def _write_to_tf_record():
with tf.Graph().as_default():
image_placeholder = tf.placeholder(dtype=tf.uint16)
encoded_image = tf.image.encode_png(image_placeholder)
label_placeholder = tf.placeholder(dtype=tf.uint16)
encoded_label = tf.image.encode_png(image_placeholder)
with tf.python_io.TFRecordWriter("./toy.tfrecord") as writer:
with tf.Session() as sess:
feed_dict = {image_placeholder: sample,
label_placeholder: label}
# Encode image and label as binary strings to be written to tf_record
image_string, label_string = sess.run(fetches=(encoded_image, encoded_label),
feed_dict=feed_dict)
# Define structure of what is going to be written
file_structure = labeled_image_to_tfexample(image_string, label_string)
writer.write(file_structure.SerializeToString())
return
However I cannot read it. First I tried (based on http://www.machinelearninguru.com/deep_learning/tensorflow/basics/tfrecord/tfrecord.html , https://medium.com/coinmonks/storage-efficient-tfrecord-for-images-6dc322b81db4 and https://medium.com/mostly-ai/tensorflow-records-what-they-are-and-how-to-use-them-c46bc4bbb564)
def read_tfrecord_low_level():
data_path = "./toy.tfrecord"
filename_queue = tf.train.string_input_producer([data_path], num_epochs=1)
reader = tf.TFRecordReader()
_, raw_records = reader.read(filename_queue)
decode_protocol = {
'sample/image': tf.FixedLenFeature((), tf.int64),
'sample/label': tf.FixedLenFeature((), tf.int64)
}
enc_example = tf.parse_single_example(raw_records, features=decode_protocol)
recovered_image = enc_example["sample/image"]
recovered_label = enc_example["sample/label"]
return recovered_image, recovered_label
I also tried variations casting enc_example and decoding it, such as in Unable to read from Tensorflow tfrecord file However when I try to evaluate them my python session just freezes and gives no output or traceback.
Then I tried using eager execution to see what is happening, but apparently it is only compatible with tf.data API. However as far as I understand transformations on tf.data API are made on the whole dataset. https://www.tensorflow.org/api_guides/python/reading_data mentions that a decode function must be written, but doesn't give an example on how to do that. All the tutorials I have found are made for TFRecordReader (which doesn't work for me).
Any help (pinpointing what I am doing wrong/ explaining what is happening/ indications on how to decode tfrecords with tf.data API) is highly appreciated.
According to https://www.youtube.com/watch?v=4oNdaQk0Qv4 and https://www.youtube.com/watch?v=uIcqeP7MFH0 tf.data is the best way to create input pipelines, so I am highly interested on learning that way.
Thanks in advance!
I am not sure why storing the encoded png causes the evaluation to not work, but here is a possible way of working around the problem. Since you mentioned that you would like to use the tf.data way of creating input pipelines, I'll show how to use it with your toy example:
label = np.asarray([[1,2,3],
[4,5,6]]).reshape(2, 3, -1)
sample = np.stack((label + 200).reshape(2, 3, -1))
First, the data has to be saved to the TFRecord file. The difference from what you did is that the image is not encoded to png.
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
writer = tf.python_io.TFRecordWriter("toy.tfrecord")
example = tf.train.Example(features=tf.train.Features(feature={
'label_raw': _bytes_feature(tf.compat.as_bytes(label.tostring())),
'sample_raw': _bytes_feature(tf.compat.as_bytes(sample.tostring()))}))
writer.write(example.SerializeToString())
writer.close()
What happens in the code above is that the arrays are turned into strings (1d objects) and then stored as bytes features.
Then, to read the data back using the tf.data.TFRecordDataset and tf.data.Iterator class:
filename = 'toy.tfrecord'
# Create a placeholder that will contain the name of the TFRecord file to use
data_path = tf.placeholder(dtype=tf.string, name="tfrecord_file")
# Create the dataset from the TFRecord file
dataset = tf.data.TFRecordDataset(data_path)
# Use the map function to read every sample from the TFRecord file (_read_from_tfrecord is shown below)
dataset = dataset.map(_read_from_tfrecord)
# Create an iterator object that enables you to access all the samples in the dataset
iterator = tf.data.Iterator.from_structure(dataset.output_types, dataset.output_shapes)
label_tf, sample_tf = iterator.get_next()
# Similarly to tf.Variables, the iterators have to be initialised
iterator_init = iterator.make_initializer(dataset, name="dataset_init")
with tf.Session() as sess:
# Initialise the iterator passing the name of the TFRecord file to the placeholder
sess.run(iterator_init, feed_dict={data_path: filename})
# Obtain the images and labels back
read_label, read_sample = sess.run([label_tf, sample_tf])
The function _read_from_tfrecord() is:
def _read_from_tfrecord(example_proto):
feature = {
'label_raw': tf.FixedLenFeature([], tf.string),
'sample_raw': tf.FixedLenFeature([], tf.string)
}
features = tf.parse_example([example_proto], features=feature)
# Since the arrays were stored as strings, they are now 1d
label_1d = tf.decode_raw(features['label_raw'], tf.int64)
sample_1d = tf.decode_raw(features['sample_raw'], tf.int64)
# In order to make the arrays in their original shape, they have to be reshaped.
label_restored = tf.reshape(label_1d, tf.stack([2, 3, -1]))
sample_restored = tf.reshape(sample_1d, tf.stack([2, 3, -1]))
return label_restored, sample_restored
Instead of hard-coding the shape [2, 3, -1], you could also store that too into the TFRecord file, but for simplicity I didn't do it.
I made a little gist with a working example.
Hope this helps!
I have the full COCO 2017 Dataset (Train,Test,Val) and i want to create tf_record files out of it.
But not for all classes, but rather for only some selected ones.
Therefore I have a label_map containing all classes i want to include in the tf_records in the following tf format:
item {
name: "/m/01g317"
id: 1
display_name: "person"
}
item {
name: "/m/0199g"
id: 2
display_name: "bicycle"
}
The standard script for creating the complete tf_record for all classes is this:
def create_tf_example(image,
annotations_list,
image_dir,
category_index,
include_masks=False):
"""Converts image and annotations to a tf.Example proto.
Args:
image: dict with keys:
[u'license', u'file_name', u'coco_url', u'height', u'width',
u'date_captured', u'flickr_url', u'id']
annotations_list:
list of dicts with keys:
[u'segmentation', u'area', u'iscrowd', u'image_id',
u'bbox', u'category_id', u'id']
Notice that bounding box coordinates in the official COCO dataset are
given as [x, y, width, height] tuples using absolute coordinates where
x, y represent the top-left (0-indexed) corner. This function converts
to the format expected by the Tensorflow Object Detection API (which is
which is [ymin, xmin, ymax, xmax] with coordinates normalized relative
to image size).
image_dir: directory containing the image files.
category_index: a dict containing COCO category information keyed
by the 'id' field of each category. See the
label_map_util.create_category_index function.
include_masks: Whether to include instance segmentations masks
(PNG encoded) in the result. default: False.
Returns:
example: The converted tf.Example
num_annotations_skipped: Number of (invalid) annotations that were ignored.
Raises:
ValueError: if the image pointed to by data['filename'] is not a valid JPEG
"""
image_height = image['height']
image_width = image['width']
filename = image['file_name']
image_id = image['id']
full_path = os.path.join(image_dir, filename)
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
key = hashlib.sha256(encoded_jpg).hexdigest()
xmin = []
xmax = []
ymin = []
ymax = []
is_crowd = []
category_names = []
category_ids = []
area = []
encoded_mask_png = []
num_annotations_skipped = 0
for object_annotations in annotations_list:
(x, y, width, height) = tuple(object_annotations['bbox'])
if width <= 0 or height <= 0:
num_annotations_skipped += 1
continue
if x + width > image_width or y + height > image_height:
num_annotations_skipped += 1
continue
xmin.append(float(x) / image_width)
xmax.append(float(x + width) / image_width)
ymin.append(float(y) / image_height)
ymax.append(float(y + height) / image_height)
is_crowd.append(object_annotations['iscrowd'])
category_id = int(object_annotations['category_id'])
category_ids.append(category_id)
category_names.append(category_index[category_id]['name'].encode('utf8'))
area.append(object_annotations['area'])
if include_masks:
run_len_encoding = mask.frPyObjects(object_annotations['segmentation'],
image_height, image_width)
binary_mask = mask.decode(run_len_encoding)
if not object_annotations['iscrowd']:
binary_mask = np.amax(binary_mask, axis=2)
pil_image = PIL.Image.fromarray(binary_mask)
output_io = io.BytesIO()
pil_image.save(output_io, format='PNG')
encoded_mask_png.append(output_io.getvalue())
feature_dict = {
'image/height':
dataset_util.int64_feature(image_height),
'image/width':
dataset_util.int64_feature(image_width),
'image/filename':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(str(image_id).encode('utf8')),
'image/key/sha256':
dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymax),
'image/object/class/label':
dataset_util.int64_list_feature(category_ids),
'image/object/is_crowd':
dataset_util.int64_list_feature(is_crowd),
'image/object/area':
dataset_util.float_list_feature(area),
}
if include_masks:
feature_dict['image/object/mask'] = (
dataset_util.bytes_list_feature(encoded_mask_png))
example = tf.train.Example(features=tf.train.Features(feature=feature_dict))
return key, example, num_annotations_skipped
def _create_tf_record_from_coco_annotations(
annotations_file, image_dir, output_path, include_masks):
"""Loads COCO annotation json files and converts to tf.Record format.
Args:
annotations_file: JSON file containing bounding box annotations.
image_dir: Directory containing the image files.
output_path: Path to output tf.Record file.
include_masks: Whether to include instance segmentations masks
(PNG encoded) in the result. default: False.
"""
with tf.gfile.GFile(annotations_file, 'r') as fid:
groundtruth_data = json.load(fid)
images = groundtruth_data['images']
category_index = label_map_util.create_category_index(
groundtruth_data['categories'])
annotations_index = {}
if 'annotations' in groundtruth_data:
tf.logging.info(
'Found groundtruth annotations. Building annotations index.')
for annotation in groundtruth_data['annotations']:
image_id = annotation['image_id']
if image_id not in annotations_index:
annotations_index[image_id] = []
annotations_index[image_id].append(annotation)
missing_annotation_count = 0
for image in images:
image_id = image['id']
if image_id not in annotations_index:
missing_annotation_count += 1
annotations_index[image_id] = []
tf.logging.info('%d images are missing annotations.',
missing_annotation_count)
tf.logging.info('writing to output path: %s', output_path)
writer = tf.python_io.TFRecordWriter(output_path)
total_num_annotations_skipped = 0
for idx, image in enumerate(images):
if idx % 100 == 0:
tf.logging.info('On image %d of %d', idx, len(images))
annotations_list = annotations_index[image['id']]
_, tf_example, num_annotations_skipped = create_tf_example(
image, annotations_list, image_dir, category_index, include_masks)
total_num_annotations_skipped += num_annotations_skipped
writer.write(tf_example.SerializeToString())
writer.close()
tf.logging.info('Finished writing, skipped %d annotations.',
total_num_annotations_skipped)
i tried to load my custom label map as category index with the label_map_util but it gives me key errors i dont know how to solve.
Has anybody an idea how to do this task?
I tried the following steps
I followed this link to generate class wise xmls based on the coco json annotations.
this will create separate folders for each class and we can select the classes required and club them all together into one folder. This results in a custom dataset of fewer objects but the XML's still contain the objects names which are not required since coco has multiple instances of different classes in same image.
then i parsed the xml for only the required objects based on their class names and ids. This left me with few xmls which are only required.
Then i used some linux commands to curate the images in the dataset based on XML names. this resulted in a separate folder with the images and annotations that are only needed.
then I created csv files using the XMLs which I fed into tf record script to generate train.record and test.record which I fed into training.
Everything worked out fine except the training stopped in the middle saying "premature end of Jpeg". I tried restarting the training from previous check point but the training again stops after certain number of steps. But the training loss seem to be converging while the training is going on. I verified the record files by their size. the tf_record file and the image folder has approximately the same size. I am now stuck at figuring this out.
Any further help is appreciated.
Thanks
I want to perform a multi-label classification with TensorFlow.
I have about 95000 images and for each image there is a corresponding label vector. For every image there are 7 labels. These 7 labels are represented as a tensor with size 7. Each image has the shape of (299,299,3).
How can I now write the image with the corresponding label vector/tensor to the .tfrecords File
my current code/approach:
def get_decode_and_resize_image(image_id):
image_queue = tf.train.string_input_producer(['../../original-data/'+image_id+".jpg"])
image_reader = tf.WholeFileReader()
image_key, image_value = image_reader.read(image_queue)
image = tf.image.decode_jpeg(image_value,channels=3)
resized_image= tf.image.resize_images(image, 299, 299, align_corners=False)
return resized_image
init_op = tf.initialize_all_variables()
with tf.Session() as sess:
# Start populating the filename queue.
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
# get all labels and image ids
csv= pd.read_csv('../../filteredLabelsToPhotos.csv')
#create a writer for writing to the .tfrecords file
writer = tf.python_io.TFRecordWriter("tfrecords/data.tfrecords")
for index,row in csv.iterrows():
# the labels
image_id = row['photo_id']
lunch = tf.to_float(row["lunch"])
dinner= tf.to_float(row["dinner"])
reservations= tf.to_float(row["TK"])
outdoor = tf.to_float(row["OS"])
waiter = tf.to_float(row["WS"])
classy = tf.to_float(row["c"])
gfk = tf.to_float(row["GFK"])
labels_list = [lunch,dinner,reservations,outdoor,waiter,classy,gfk]
labels_tensor = tf.convert_to_tensor(labels_list)
#get the corresponding image
image_file= get_decode_and_resize_image(image_id=image_id)
#here : how do I now create a TFExample and write it to the .tfrecords file
coord.request_stop()
coord.join(threads)
And after I´ve created the .tfrecords file, can i then read it from my TensorFlow Training Code and batch the data automatically?
To expand on Alexandre's answer, you can do something like this:
# Set this up before your for-loop, you'll use this repeatedly
tfrecords_filename = 'myfile.tfrecords'
writer = tf.python_io.TFRecordWriter(tfrecords_filename)
# Then within your for-loop, you can write like so:
for ...:
#here : how do I now create a TFExample and write it to the .tfrecords file
example = tf.train.Example(features=tf.train.Features(feature={
'image_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_file])),
# the other features, labels you wish to include go here too
}))
writer.write(example.SerializeToString())
# then finally, don't forget to close the writer.
writer.close()
This assumes you have already converted the image into a byte array in the image_file variable.
I adapted this from this very helpful post that goes into detail on serialising images & may be helpful to you if my assumption above is false.
To create a tf.train.Example simply do example = tf.train.Example(). You can then manipulate it using the normal protocol buffers python API.
I have training data that is a directory of jpeg images and a corresponding text file containing the file name and the associated category label. I am trying to convert this training data into a tfrecords file as described in the tensorflow documentation. I have spent quite some time trying to get this to work but there are no examples in tensorflow that demonstrate how to use any of the readers to read in jpeg files and add them to a tfrecord using tfrecordwriter
I hope this helps:
filename_queue = tf.train.string_input_producer(['/Users/HANEL/Desktop/tf.png']) # list of files to read
reader = tf.WholeFileReader()
key, value = reader.read(filename_queue)
my_img = tf.image.decode_png(value) # use decode_png or decode_jpeg decoder based on your files.
init_op = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init_op)
# Start populating the filename queue.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for i in range(1): #length of your filename list
image = my_img.eval() #here is your image Tensor :)
print(image.shape)
Image.show(Image.fromarray(np.asarray(image)))
coord.request_stop()
coord.join(threads)
For getting all images as an array of tensors use the following code example.
Github repo of ImageFlow
Update:
In the previous answer I just told how to read an image in TF format, but not saving it in TFRecords. For that you should use:
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
# images and labels array as input
def convert_to(images, labels, name):
num_examples = labels.shape[0]
if images.shape[0] != num_examples:
raise ValueError("Images size %d does not match label size %d." %
(images.shape[0], num_examples))
rows = images.shape[1]
cols = images.shape[2]
depth = images.shape[3]
filename = os.path.join(FLAGS.directory, name + '.tfrecords')
print('Writing', filename)
writer = tf.python_io.TFRecordWriter(filename)
for index in range(num_examples):
image_raw = images[index].tostring()
example = tf.train.Example(features=tf.train.Features(feature={
'height': _int64_feature(rows),
'width': _int64_feature(cols),
'depth': _int64_feature(depth),
'label': _int64_feature(int(labels[index])),
'image_raw': _bytes_feature(image_raw)}))
writer.write(example.SerializeToString())
More info here
And you read the data like this:
# Remember to generate a file name queue of you 'train.TFRecord' file path
def read_and_decode(filename_queue):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
dense_keys=['image_raw', 'label'],
# Defaults are not specified since both keys are required.
dense_types=[tf.string, tf.int64])
# Convert from a scalar string tensor (whose single string has
image = tf.decode_raw(features['image_raw'], tf.uint8)
image = tf.reshape(image, [my_cifar.n_input])
image.set_shape([my_cifar.n_input])
# OPTIONAL: Could reshape into a 28x28 image and apply distortions
# here. Since we are not applying any distortions in this
# example, and the next step expects the image to be flattened
# into a vector, we don't bother.
# Convert from [0, 255] -> [-0.5, 0.5] floats.
image = tf.cast(image, tf.float32)
image = tf.cast(image, tf.float32) * (1. / 255) - 0.5
# Convert label from a scalar uint8 tensor to an int32 scalar.
label = tf.cast(features['label'], tf.int32)
return image, label
Tensorflow's inception model has a file build_image_data.py that can accomplish the same thing with the assumption that each subdirectory represents a label.
Note that images will be saved in TFRecord as uncompressed tensors, possibly increasing the size by a factor of about 5. That's wasting storage space, and likely to be rather slow because of the amount of data that needs to be read.
It's far better to just save the filename in the TFRecord, and read the file on demand. The new Dataset API works well, and the documentation has this example:
# Reads an image from a file, decodes it into a dense tensor, and resizes it
# to a fixed shape.
def _parse_function(filename, label):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_jpeg(image_string)
image_resized = tf.image.resize_images(image_decoded, [28, 28])
return image_resized, label
# A vector of filenames.
filenames = tf.constant(["/var/data/image1.jpg", "/var/data/image2.jpg", ...])
# `labels[i]` is the label for the image in `filenames[i].
labels = tf.constant([0, 37, ...])
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))
dataset = dataset.map(_parse_function)
I have same problem, too.
So here is how i get the tfrecords files of my own jpeg files
Edit: add sol 1 - a better & faster way
update: Jan/5/2020
(Recommended) Solution 1: TFRecordWriter
See this Tfrecords Guide post
Solution 2:
From tensorflow official github: How to Construct a New Dataset for Retraining, use official python script build_image_data.py directly and bazel is a better idea.
Here is the instruction:
To run build_image_data.py, you can run the following command line:
# location to where to save the TFRecord data.
OUTPUT_DIRECTORY=$HOME/my-custom-data/
# build the preprocessing script.
bazel build inception/build_image_data
# convert the data.
bazel-bin/inception/build_image_data \
--train_directory="${TRAIN_DIR}" \
--validation_directory="${VALIDATION_DIR}" \
--output_directory="${OUTPUT_DIRECTORY}" \
--labels_file="${LABELS_FILE}" \
--train_shards=128 \
--validation_shards=24 \
--num_threads=8
where the $OUTPUT_DIRECTORY is the location of the sharded
TFRecords. The $LABELS_FILE will be a text file that is read by
the script that provides a list of all of the labels.
then, it should do the trick.
ps. bazel, which is made by Google, turn code into makefile.
Solution 3:
First, i reference the instruction by #capitalistpug and check the shell script file
(shell script file providing by Google: download_and_preprocess_flowers.sh)
Second, i also find out a mini inception-v3 training tutorial by NVIDIA
(NVIDIA official SPEED UP TRAINING WITH GPU-ACCELERATED TENSORFLOW)
Be careful, the following steps need to be executed in the Bazel WORKSAPCE enviroment
so Bazel build file can run successfully
First step, I comment out the part of downloading the imagenet data set that i already downloaded
and the rest of the part that i don't need of download_and_preprocess_flowers.sh
Second step, change directory to tensorflow/models/inception
where it is the Bazel environment and it is build by Bazel before
$ cd tensorflow/models/inception
Optional : If it is not builded before, type in the following code in cmd
$ bazel build inception/download_and_preprocess_flowers
You need to figure out the content in the following image
And last step, type in the following code:
$ bazel-bin/inception/download_and_preprocess_flowers $Your/own/image/data/path
Then, it will start calling build_image_data.py and creating tfrecords file
Try this script:
(used with VOC segmentation dataset:http://host.robots.ox.ac.uk/pascal/VOC/voc2012/)
import numpy as np
import tensorflow as tf
import scipy.io # to read .mat files
from PIL import Image # to read image files
def get_image(path):
jpg = Image.open(path).convert('RGB')
return np.array(jpg)
def get_label_png(path):
png = Image.open(path) # image is saved as palettised png.
arr = np.array(png)
return arr[..., None]
def get_example(image, label):
feature = {
'height': tf.train.Feature(int64_list=tf.train.Int64List(value=[image.shape[0]])),
'width': tf.train.Feature(int64_list=tf.train.Int64List(value=[image.shape[1]])),
'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image.tobytes()])),
'label': tf.train.Feature(bytes_list=tf.train.BytesList(value=[label.tobytes()]))
}
return tf.train.Example(features=tf.train.Features(feature=feature))
## Paths ======================================
images_folder = 'data/images/' #images folder
labels_folder = 'data/labels/' #label folder
train_file = 'data/train.txt'
val_file = 'data/val.txt'
TRAIN = 'data/train.tfrecords'
VAL = 'data/val.tfrecords'
## write train dataset
with tf.io.TFRecordWriter(TRAIN) as writer:
with open(train_file) as file:
filenames = [s.rstrip('\n') for s in file.readlines()]
for name in filenames:
image = utils.get_image(images_folder+name+'.jpg')
label = utils.get_label_png(labels_folder+name+'.png')
writer.write(utils.get_example(image, label).SerializeToString())
## write validation dataset
with tf.io.TFRecordWriter(VAL) as writer:
with open(val_file) as file:
filenames = [s.rstrip('\n') for s in file.readlines()]
for name in filenames:
image = utils.get_image(images_folder+name+'.jpg')
label = utils.get_label_png(labels_folder+name+'.png')
writer.write(utils.get_example(image, label).SerializeToString())
Mentioning the Code in the Link specified by Kamil, so that the code will be available even if the Link is broken.
"""Converts image data to TFRecords file format with Example protos.
If your data set involves bounding boxes, please look at build_imagenet_data.py.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from datetime import datetime
import os
import random
import sys
import threading
import numpy as np
import tensorflow as tf
tf.app.flags.DEFINE_string('train_directory', '/tmp/',
'Training data directory')
tf.app.flags.DEFINE_string('validation_directory', '/tmp/',
'Validation data directory')
tf.app.flags.DEFINE_string('output_directory', '/tmp/',
'Output data directory')
tf.app.flags.DEFINE_integer('train_shards', 2,
'Number of shards in training TFRecord files.')
tf.app.flags.DEFINE_integer('validation_shards', 2,
'Number of shards in validation TFRecord files.')
tf.app.flags.DEFINE_integer('num_threads', 2,
'Number of threads to preprocess the images.')
# The labels file contains a list of valid labels are held in this file.
# Assumes that the file contains entries as such:
# dog
# cat
# flower
# where each line corresponds to a label. We map each label contained in
# the file to an integer corresponding to the line number starting from 0.
tf.app.flags.DEFINE_string('labels_file', '', 'Labels file')
FLAGS = tf.app.flags.FLAGS
def _int64_feature(value):
"""Wrapper for inserting int64 features into Example proto."""
if not isinstance(value, list):
value = [value]
return tf.train.Feature(int64_list=tf.train.Int64List(value=value))
def _bytes_feature(value):
"""Wrapper for inserting bytes features into Example proto."""
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def _convert_to_example(filename, image_buffer, label, text, height, width):
"""Build an Example proto for an example.
Args:
filename: string, path to an image file, e.g., '/path/to/example.JPG'
image_buffer: string, JPEG encoding of RGB image
label: integer, identifier for the ground truth for the network
text: string, unique human-readable, e.g. 'dog'
height: integer, image height in pixels
width: integer, image width in pixels
Returns:
Example proto
"""
colorspace = 'RGB'
channels = 3
image_format = 'JPEG'
example = tf.train.Example(features=tf.train.Features(feature={
'image/height': _int64_feature(height),
'image/width': _int64_feature(width),
'image/colorspace': _bytes_feature(tf.compat.as_bytes(colorspace)),
'image/channels': _int64_feature(channels),
'image/class/label': _int64_feature(label),
'image/class/text': _bytes_feature(tf.compat.as_bytes(text)),
'image/format': _bytes_feature(tf.compat.as_bytes(image_format)),
'image/filename': _bytes_feature(tf.compat.as_bytes(os.path.basename(filename))),
'image/encoded': _bytes_feature(tf.compat.as_bytes(image_buffer))}))
return example
class ImageCoder(object):
"""Helper class that provides TensorFlow image coding utilities."""
def __init__(self):
# Create a single Session to run all image coding calls.
self._sess = tf.Session()
# Initializes function that converts PNG to JPEG data.
self._png_data = tf.placeholder(dtype=tf.string)
image = tf.image.decode_png(self._png_data, channels=3)
self._png_to_jpeg = tf.image.encode_jpeg(image, format='rgb', quality=100)
# Initializes function that decodes RGB JPEG data.
self._decode_jpeg_data = tf.placeholder(dtype=tf.string)
self._decode_jpeg = tf.image.decode_jpeg(self._decode_jpeg_data, channels=3)
def png_to_jpeg(self, image_data):
return self._sess.run(self._png_to_jpeg,
feed_dict={self._png_data: image_data})
def decode_jpeg(self, image_data):
image = self._sess.run(self._decode_jpeg,
feed_dict={self._decode_jpeg_data: image_data})
assert len(image.shape) == 3
assert image.shape[2] == 3
return image
def _is_png(filename):
"""Determine if a file contains a PNG format image.
Args:
filename: string, path of the image file.
Returns:
boolean indicating if the image is a PNG.
"""
return '.png' in filename
def _process_image(filename, coder):
"""Process a single image file.
Args:
filename: string, path to an image file e.g., '/path/to/example.JPG'.
coder: instance of ImageCoder to provide TensorFlow image coding utils.
Returns:
image_buffer: string, JPEG encoding of RGB image.
height: integer, image height in pixels.
width: integer, image width in pixels.
"""
# Read the image file.
with tf.gfile.FastGFile(filename, 'rb') as f:
image_data = f.read()
# Convert any PNG to JPEG's for consistency.
if _is_png(filename):
print('Converting PNG to JPEG for %s' % filename)
image_data = coder.png_to_jpeg(image_data)
# Decode the RGB JPEG.
image = coder.decode_jpeg(image_data)
# Check that image converted to RGB
assert len(image.shape) == 3
height = image.shape[0]
width = image.shape[1]
assert image.shape[2] == 3
return image_data, height, width
def _process_image_files_batch(coder, thread_index, ranges, name, filenames,
texts, labels, num_shards):
"""Processes and saves list of images as TFRecord in 1 thread.
Args:
coder: instance of ImageCoder to provide TensorFlow image coding utils.
thread_index: integer, unique batch to run index is within [0, len(ranges)).
ranges: list of pairs of integers specifying ranges of each batches to
analyze in parallel.
name: string, unique identifier specifying the data set
filenames: list of strings; each string is a path to an image file
texts: list of strings; each string is human readable, e.g. 'dog'
labels: list of integer; each integer identifies the ground truth
num_shards: integer number of shards for this data set.
"""
# Each thread produces N shards where N = int(num_shards / num_threads).
# For instance, if num_shards = 128, and the num_threads = 2, then the first
# thread would produce shards [0, 64).
num_threads = len(ranges)
assert not num_shards % num_threads
num_shards_per_batch = int(num_shards / num_threads)
shard_ranges = np.linspace(ranges[thread_index][0],
ranges[thread_index][1],
num_shards_per_batch + 1).astype(int)
num_files_in_thread = ranges[thread_index][1] - ranges[thread_index][0]
counter = 0
for s in range(num_shards_per_batch):
# Generate a sharded version of the file name, e.g. 'train-00002-of-00010'
shard = thread_index * num_shards_per_batch + s
output_filename = '%s-%.5d-of-%.5d' % (name, shard, num_shards)
output_file = os.path.join(FLAGS.output_directory, output_filename)
writer = tf.python_io.TFRecordWriter(output_file)
shard_counter = 0
files_in_shard = np.arange(shard_ranges[s], shard_ranges[s + 1], dtype=int)
for i in files_in_shard:
filename = filenames[i]
label = labels[i]
text = texts[i]
try:
image_buffer, height, width = _process_image(filename, coder)
except Exception as e:
print(e)
print('SKIPPED: Unexpected eror while decoding %s.' % filename)
continue
example = _convert_to_example(filename, image_buffer, label,
text, height, width)
writer.write(example.SerializeToString())
shard_counter += 1
counter += 1
if not counter % 1000:
print('%s [thread %d]: Processed %d of %d images in thread batch.' %
(datetime.now(), thread_index, counter, num_files_in_thread))
sys.stdout.flush()
writer.close()
print('%s [thread %d]: Wrote %d images to %s' %
(datetime.now(), thread_index, shard_counter, output_file))
sys.stdout.flush()
shard_counter = 0
print('%s [thread %d]: Wrote %d images to %d shards.' %
(datetime.now(), thread_index, counter, num_files_in_thread))
sys.stdout.flush()
def _process_image_files(name, filenames, texts, labels, num_shards):
"""Process and save list of images as TFRecord of Example protos.
Args:
name: string, unique identifier specifying the data set
filenames: list of strings; each string is a path to an image file
texts: list of strings; each string is human readable, e.g. 'dog'
labels: list of integer; each integer identifies the ground truth
num_shards: integer number of shards for this data set.
"""
assert len(filenames) == len(texts)
assert len(filenames) == len(labels)
# Break all images into batches with a [ranges[i][0], ranges[i][1]].
spacing = np.linspace(0, len(filenames), FLAGS.num_threads + 1).astype(np.int)
ranges = []
for i in range(len(spacing) - 1):
ranges.append([spacing[i], spacing[i + 1]])
# Launch a thread for each batch.
print('Launching %d threads for spacings: %s' % (FLAGS.num_threads, ranges))
sys.stdout.flush()
# Create a mechanism for monitoring when all threads are finished.
coord = tf.train.Coordinator()
# Create a generic TensorFlow-based utility for converting all image codings.
coder = ImageCoder()
threads = []
for thread_index in range(len(ranges)):
args = (coder, thread_index, ranges, name, filenames,
texts, labels, num_shards)
t = threading.Thread(target=_process_image_files_batch, args=args)
t.start()
threads.append(t)
# Wait for all the threads to terminate.
coord.join(threads)
print('%s: Finished writing all %d images in data set.' %
(datetime.now(), len(filenames)))
sys.stdout.flush()
def _find_image_files(data_dir, labels_file):
"""Build a list of all images files and labels in the data set.
Args:
data_dir: string, path to the root directory of images.
Assumes that the image data set resides in JPEG files located in
the following directory structure.
data_dir/dog/another-image.JPEG
data_dir/dog/my-image.jpg
where 'dog' is the label associated with these images.
labels_file: string, path to the labels file.
The list of valid labels are held in this file. Assumes that the file
contains entries as such:
dog
cat
flower
where each line corresponds to a label. We map each label contained in
the file to an integer starting with the integer 0 corresponding to the
label contained in the first line.
Returns:
filenames: list of strings; each string is a path to an image file.
texts: list of strings; each string is the class, e.g. 'dog'
labels: list of integer; each integer identifies the ground truth.
"""
print('Determining list of input files and labels from %s.' % data_dir)
unique_labels = [l.strip() for l in tf.gfile.FastGFile(
labels_file, 'r').readlines()]
labels = []
filenames = []
texts = []
# Leave label index 0 empty as a background class.
label_index = 1
# Construct the list of JPEG files and labels.
for text in unique_labels:
jpeg_file_path = '%s/%s/*' % (data_dir, text)
matching_files = tf.gfile.Glob(jpeg_file_path)
labels.extend([label_index] * len(matching_files))
texts.extend([text] * len(matching_files))
filenames.extend(matching_files)
if not label_index % 100:
print('Finished finding files in %d of %d classes.' % (
label_index, len(labels)))
label_index += 1
# Shuffle the ordering of all image files in order to guarantee
# random ordering of the images with respect to label in the
# saved TFRecord files. Make the randomization repeatable.
shuffled_index = list(range(len(filenames)))
random.seed(12345)
random.shuffle(shuffled_index)
filenames = [filenames[i] for i in shuffled_index]
texts = [texts[i] for i in shuffled_index]
labels = [labels[i] for i in shuffled_index]
print('Found %d JPEG files across %d labels inside %s.' %
(len(filenames), len(unique_labels), data_dir))
return filenames, texts, labels
def _process_dataset(name, directory, num_shards, labels_file):
"""Process a complete data set and save it as a TFRecord.
Args:
name: string, unique identifier specifying the data set.
directory: string, root path to the data set.
num_shards: integer number of shards for this data set.
labels_file: string, path to the labels file.
"""
filenames, texts, labels = _find_image_files(directory, labels_file)
_process_image_files(name, filenames, texts, labels, num_shards)
def main(unused_argv):
assert not FLAGS.train_shards % FLAGS.num_threads, (
'Please make the FLAGS.num_threads commensurate with FLAGS.train_shards')
assert not FLAGS.validation_shards % FLAGS.num_threads, (
'Please make the FLAGS.num_threads commensurate with '
'FLAGS.validation_shards')
print('Saving results to %s' % FLAGS.output_directory)
# Run it!
_process_dataset('validation', FLAGS.validation_directory,
FLAGS.validation_shards, FLAGS.labels_file)
_process_dataset('train', FLAGS.train_directory,
FLAGS.train_shards, FLAGS.labels_file)
if __name__ == '__main__':
tf.app.run()
In case of too much size in tfrecord files you use directly read bytes.
This link shows it.
TFrecords occupy more space than original JPEG images
you use this function to read bytes directly.
img_bytes = open(path,'rb').read()
reference
https://github.com/tensorflow/tensorflow/issues/9675
You can use the Kubeflow pipeline here to do the conversion:
https://aihub.cloud.google.com/u/0/p/products%2Fded3e5e5-d2e8-4d65-9b9f-5ffaa9a27ea1
Click on the Download link (create a Kubeflow cluster to run the pipeline)