I'm working on a project do detect faces and I'm using the following code:
# demonstrate face detection on 5 Celebrity Faces Dataset
from os import listdir
from PIL import Image
from numpy import asarray
from matplotlib import pyplot
from mtcnn.mtcnn import MTCNN
# extract a single face from a given photograph
def extract_face(filename, required_size=(160, 160)):
# load image from file
image = Image.open(filename)
# convert to RGB, if needed
image = image.convert('RGB')
# convert to array
pixels = asarray(image)
# create the detector, using default weights
detector = MTCNN()
# detect faces in the image
results = detector.detect_faces(pixels)
# extract the bounding box from the first face
x1, y1, width, height = results[0]['box']
# bug fix
x1, y1 = abs(x1), abs(y1)
x2, y2 = x1 + width, y1 + height
# extract the face
face = pixels[y1:y2, x1:x2]
# resize pixels to the model size
image = Image.fromarray(face)
image = image.resize(required_size)
face_array = asarray(image)
return face_array
# specify folder to plot
#folder = '5-celebrity-faces-dataset/train/ben_afflek/'
folder = '/content/drive/My Drive/ufc-project/5-celebrity-faces-dataset/train/ben_afflek'
i = 1
# enumerate files
for filename in listdir(folder):
# path
path = folder + '/' + filename
# get face
face = extract_face(path)
print(i, face.shape)
# plot
pyplot.subplot(2, 7, i)
pyplot.axis('off')
pyplot.imshow(face)
i += 1
pyplot.show()
I got this code from this tutorial: https://machinelearningmastery.com/how-to-develop-a-face-recognition-system-using-facenet-in-keras-and-an-svm-classifier/?unapproved=549711&moderation-hash=6b355b586de2f2ff191df14529849990#comment-549711
It's working, but I'm getting the following warning:
WARNING:tensorflow:6 out of the last 11 calls to <function Model.make_predict_function..predict_function at 0x7f0016e2eae8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating #tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your #tf.function outside of the loop. For (2), #tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.
Does anyone know how to fix it?
You are creating the detector each time you call extract face. Move the face detector creation out from the loop and pass it as an argument to the function.
Move the line detector = MTCNN() outside of extract_face specifically before the loop.
I am currently using tensorboardX to visualize input images while training a ResNet image classifier. Is there a way to add the image title along with the added image? I would like to have the image name (as stored in the dataset) displayed below the image in the tensorboard display.
So far I have tried passing a comment parameter into my tensorboard writer, which does not seem to do the job.
Currently, the relevant lines of my code are:
pretrain_train_writer = SummaryWriter('log/pretrain_train')
img_grid = vutils.make_grid(inputs[tp_idx_0], normalize=True, scale_each=True, nrow=8)
pretrain_val_writer.add_image('true_positive_class_0', img_grid, global_step=epoch, comment = img_path)
there is no way of doing it directly with tensorboard, instead you have to create images with titles using matplotlib and then supply them to tensorboard. Here is a sample code from the tensorboard documentation:
def plot_to_image(figure):
"""Converts the matplotlib plot specified by 'figure' to a PNG image and
returns it. The supplied figure is closed and inaccessible after this call."""
# Save the plot to a PNG in memory.
buf = io.BytesIO()
plt.savefig(buf, format='png')
# Closing the figure prevents it from being displayed directly inside
# the notebook.
plt.close(figure)
buf.seek(0)
# Convert PNG buffer to TF image
image = tf.image.decode_png(buf.getvalue(), channels=4)
# Add the batch dimension
image = tf.expand_dims(image, 0)
return image
def image_grid():
"""Return a 5x5 grid of the MNIST images as a matplotlib figure."""
# Create a figure to contain the plot.
figure = plt.figure(figsize=(10,10))
for i in range(25):
# Start next subplot.
plt.subplot(5, 5, i + 1, title=class_names[train_labels[i]])
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(train_images[i], cmap=plt.cm.binary)
return figure
# Prepare the plot
figure = image_grid()
# Convert to image and log
with file_writer.as_default():
tf.summary.image("Training data", plot_to_image(figure), step=0)
here is the link to the doc: https://www.tensorflow.org/tensorboard/image_summaries
I've been trying to use a hyperspectral image dataset that was in .mat files. I found that using the scipy library with its loadmat function I can load the hyperspectral images and selecting some bands to see them as an RGB.
def RGBread(image):
images = loadmat(image).get('new_image')
return abs(images[:,:,(12,6,4)])
def SIread(image):
images = loadmat(image).get('new_image')
return abs(images[:,:,:])
After trying to implement the pix2pix architecture I found an unexpected error. When passing the list of the names of the dataset files by a function that is responsible for load the data(which are still .mat files), Tensor Flow does not have a direct method for this reading or coding, so I get these data with my RGBread and SIread method and then I turned them into tensors.
def load_image(filename, augment=True):
inimg = tf.cast( tf.convert_to_tensor(RGBread(ImagePATH+'/'+filename)
,dtype=tf.float32),tf.float32)[...,:3]
tgimg = tf.cast( tf.convert_to_tensor(SIread(ImagePATH+'/'+filename)
,dtype=tf.float32),tf.float32)[...,:12]
inimg, tgimg = resize(inimg, tgimg,IMG_HEIGH,IMG_WIDTH)
if augment:
inimg, tgimg = random_jitter(inimg, tgimg)
return inimg, tgimg
When loading an image with the load_image method, using the name and path of a single .mat file (a hyperspectral image) of my dataset as argument of my function the method worked perfectly.
plt.imshow(load_train_image(tr_urls[1])[0])
The problem started when I created my dataSet tensor, because my RGBread function does not receive a tensor as a parameter since loadmat('.mat') expects a string. Having the following error.
train_dataset = tf.data.Dataset.from_tensor_slices(tr_urls)
train_dataset = train_dataset.map(load_train_image,
num_parallel_calls=tf.data.experimental.AUTOTUNE)
TypeError: expected str, bytes or os.PathLike object, not Tensor
After reading a lot about reading .mat files I found a user who recommended passing the data to TFrecord format. I've been trying to do it but I couldn't. Someone could help me?
Rasterio may be useful here.
https://rasterio.readthedocs.io/en/latest/
It can read hyperspectral .tif which can be passed to tf.data using a tf.keras data-generator. It may be a bit slow and perhaps should be done before training rather than at runtime.
An alternative is to ask whether you need the geotiff metadata. If not, you can preprocess and save as numpy arrays for tfrecords.
I'm trying to run https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/learn/text_classification_character_cnn.py for learning, but I get an error message:
File "C:\Users\natlun\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\base.py", line 72, in load_csv_without_header
data = np.array(data)
MemoryError
I use CPU installation of TensorFlow and Python 3.5. Any ideas how to solve the problem?? Other scripts using a csv-file for input work fine.
I was having the same issue. And after many hours of reading and googling (and seeing your unanswered question), and just comparing the example with other examples that do run, I noticed that
dbpedia = tf.contrib.learn.datasets.load_dataset(
'dbpedia', test_with_fake_data=FLAGS.test_with_fake_data, size='large')
should just be
dbpedia = tf.contrib.learn.datasets.load_dataset(
'dbpedia', test_with_fake_data=FLAGS.test_with_fake_data)
Based off of what I've read about numpy, I'd bet the "size='large'" parameter causes an over allocation to a numpy array (which throws the memory error).
Or, when you don't set that parameter perhaps the input data is truncated.
Or some other thing. Anyway, I hope this helps others attempting to run this useful example!
--- Update ---
Without "size='large'" the load_dataset functions appears to create smaller training and test data sets (like 1/1000 the size).
After playing around with the example I realized I could manually load and use the whole data set without getting the memory error (assume it is saving the whole data set as it appears).
# Prepare training and testing data
##This was the provided method for setting up the data.
# dbpedia = tf.contrib.learn.datasets.load_dataset(
# 'dbpedia', test_with_fake_data=FLAGS.test_with_fake_data)
# x_trainz = pandas.DataFrame(dbpedia.train.data)[1]
# y_trainz = pandas.Series(dbpedia.train.target)
# x_testz = pandas.DataFrame(dbpedia.test.data)[1]
# y_testz = pandas.Series(dbpedia.test.target)
##And this is my replacement.
x_train = []
y_train = []
x_test = []
y_test = []
with open("dbpedia_data/dbpedia_csv/train.csv", encoding='utf-8') as filex:
reader = csv.reader(filex)
for row in reader:
x_train.append(row[2])
y_train.append(int(row[0]))
with open("dbpedia_data/dbpedia_csv/test.csv", encoding='utf-8') as filex:
reader = csv.reader(filex)
for row in reader:
x_test.append(row[2])
y_test.append(int(row[0]))
x_train = pandas.Series(x_train)
y_train = pandas.Series(y_train)
x_test = pandas.Series(x_test)
y_test = pandas.Series(y_test)
The example seems to now be evaluating the whole training data set. But, the original code will probably need to be run once to get/put the data in the correct sub-folders. Also, even while evaluating the whole data set little memory is used (just a few hundred MB). Which, makes me think that the load_dataset function is broken in some way.
I have read the CNN Tutorial on the TensorFlow and I am trying to use the same model for my project.
The problem is now in data reading. I have around 25000 images for training and around 5000 for testing and validation each. The files are in png format and I can read them and convert them into the numpy.ndarray.
The CNN example in the tutorials use a queue to fetch the records from the file list provided. I tried to create my own such binary file by reshaping my images into 1-D array and attaching a label value in the front of it. So my data looks like this
[[1,12,34,24,53,...,105,234,102],
[12,112,43,24,52,...,115,244,98],
....
]
The single row of the above array is of length 22501 size where the first element is the label.
I dumped the file to using pickle and the tried to read from the file using the
tf.FixedLengthRecordReader to read from the file as demonstrated in example
I am doing the same things as given in the cifar10_input.py to read the binary file and putting them into the record object.
Now when I read from the files the labels and the image values are different. I can understand the reason for this to be that pickle dumps the extra information of braces and brackets also in the binary file and they change the fixed length record size.
The above example uses the filenames and pass it to a queue to fetch the files and then the queue to read a single record from the file.
I want to know if I can pass the numpy array as defined above instead of the filenames to some reader and it can fetch records one by one from that array instead of the files.
Probably the easiest way to make your data work with the CNN example code is to make a modified version of read_cifar10() and use it instead:
Write out a binary file containing the contents of your numpy array.
import numpy as np
images_and_labels_array = np.array([[...], ...], # [[1,12,34,24,53,...,102],
# [12,112,43,24,52,...,98],
# ...]
dtype=np.uint8)
images_and_labels_array.tofile("/tmp/images.bin")
This file is similar to the format used in CIFAR10 datafiles. You might want to generate multiple files in order to get read parallelism. Note that ndarray.tofile() writes binary data in row-major order with no other metadata; pickling the array will add Python-specific metadata that TensorFlow's parsing routines do not understand.
Write a modified version of read_cifar10() that handles your record format.
def read_my_data(filename_queue):
class ImageRecord(object):
pass
result = ImageRecord()
# Dimensions of the images in the dataset.
label_bytes = 1
# Set the following constants as appropriate.
result.height = IMAGE_HEIGHT
result.width = IMAGE_WIDTH
result.depth = IMAGE_DEPTH
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
assert record_bytes == 22501 # Based on your question.
# Read a record, getting filenames from the filename_queue. No
# header or footer in the binary, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(tf.slice(record_bytes, [label_bytes], [image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
Modify distorted_inputs() to use your new dataset:
def distorted_inputs(data_dir, batch_size):
"""[...]"""
filenames = ["/tmp/images.bin"] # Or a list of filenames if you
# generated multiple files in step 1.
for f in filenames:
if not gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_my_data(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
# [...] (Maybe modify other parameters in here depending on your problem.)
This is intended to be a minimal set of steps, given your starting point. It may be more efficient to do the PNG decoding using TensorFlow ops, but that would be a larger change.
In your question, you specifically asked:
I want to know if I can pass the numpy array as defined above instead of the filenames to some reader and it can fetch records one by one from that array instead of the files.
You can feed the numpy array to a queue directly, but it will be a more invasive change to the cifar10_input.py code than my other answer suggests.
As before, let's assume you have the following array from your question:
import numpy as np
images_and_labels_array = np.array([[...], ...], # [[1,12,34,24,53,...,102],
# [12,112,43,24,52,...,98],
# ...]
dtype=np.uint8)
You can then define a queue that contains the entire data as follows:
q = tf.FIFOQueue([tf.uint8, tf.uint8], shapes=[[], [22500]])
enqueue_op = q.enqueue_many([image_and_labels_array[:, 0], image_and_labels_array[:, 1:]])
...then call sess.run(enqueue_op) to populate the queue.
Another—more efficient—approach would be to feed records to the queue, which you could do from a parallel thread (see this answer for more details on how this would work):
# [With q as defined above.]
label_input = tf.placeholder(tf.uint8, shape=[])
image_input = tf.placeholder(tf.uint8, shape=[22500])
enqueue_single_from_feed_op = q.enqueue([label_input, image_input])
# Then, to enqueue a single example `i` from the array.
sess.run(enqueue_single_from_feed_op,
feed_dict={label_input: image_and_labels_array[i, 0],
image_input: image_and_labels_array[i, 1:]})
Alternatively, to enqueue a batch at a time, which will be more efficient:
label_batch_input = tf.placeholder(tf.uint8, shape=[None])
image_batch_input = tf.placeholder(tf.uint8, shape=[None, 22500])
enqueue_batch_from_feed_op = q.enqueue([label_batch_input, image_batch_input])
# Then, to enqueue a batch examples `i` through `j-1` from the array.
sess.run(enqueue_single_from_feed_op,
feed_dict={label_input: image_and_labels_array[i:j, 0],
image_input: image_and_labels_array[i:j, 1:]})
I want to know if I can pass the numpy array as defined above instead
of the filenames to some reader and it can fetch records one by one
from that array instead of the files.
tf.py_func, that wraps a python function and uses it as a TensorFlow operator, might help. Here's an example.
However, since you've mentioned that your images are stored in png files, I think the simplest solution would be to replace this:
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
with this:
result.key, value = tf.WholeFileReader().read(filename_queue))
value = tf.image.decode_jpeg(value)