I am trying to do image classification using Keras's Xception model modeled after this code. However I want to use multiple GPU's to do batch parallel image classification using this function. I believe it is possible and I have the original code working without multi GPU support however I can not get multi_gpu_model function to work as I would expect. I am following this example for the multi GPU example. This is my code (it is the backend of a Flask app), it instantiates the model, makes a prediction on an example ndarray when the class is created, and then expects a base 64 encoded image in the classify function:
import os
from keras.preprocessing import image as preprocess_image
from keras.applications import Xception
from keras.applications.inception_v3 import preprocess_input, decode_predictions
from keras.utils import multi_gpu_model
import numpy as np
import tensorflow as tf
import PIL.Image
from numpy import array
class ModelManager:
def __init__(self, model_path):
self.model_name = 'ImageNet'
self.model_version = '1.0'
self.batch_size = 32
height = 224
width = 224
num_classes = 1000
# self.model = tf.keras.models.load_model(os.path.join(model_path, 'ImageNetXception.h5'))
with tf.device('/cpu:0'):
model = Xception(weights=None,
input_shape=(height, width, 3),
classes=num_classes, include_top=True)
# Replicates the model on 8 GPUs.
# This assumes that your machine has 8 available GPUs.
self.parallel_model = multi_gpu_model(model, gpus=8)
self.parallel_model.compile(loss='categorical_crossentropy',
optimizer='rmsprop')
print("Loaded Xception model.")
x = np.empty((1, 224, 224, 3))
self.parallel_model.predict(x, batch_size=self.batch_size)
self.graph = tf.get_default_graph()
self.graph.finalize()
def classify(self, ids, images):
results = []
all_images = np.empty((0, 224, 224, 3))
# all_images = []
for image_id, image in zip(ids, images):
# This does the same as keras.preprocessing.image.load_img
image = image.convert('RGB')
image = image.resize((224, 224), PIL.Image.NEAREST)
x = preprocess_image.img_to_array(image)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
all_images = np.append(all_images, x, axis=0)
# all_images.append(x)
# a = array(all_images)
# print(type(a))
# print(a[0])
with self.graph.as_default():
preds = self.parallel_model.predict(all_images, batch_size=288)
#print(type(preds))
top3 = decode_predictions(preds, top=3)[0]
print(top3)
output = [((t[1],) + t[2:]) for t in top3]
predictions = [
{'label': label, 'probability': probability * 100.0}
for label, probability in output
]
results.append({
'id': 1,
'predictions': predictions
})
print(len(results))
return results
The parts I am not sure about is what to pass the predict function. Currently I am creating an ndarray of the images I want classified after they are preprocessed and then passing that to the predict function. The function returns but the preds variable doesn't hold what I expect. I tried to loop through the preds object but decode_predictions errors when I pass a single item but responds with one prediction when I pass the whole preds ndarray. In the example code they don't use the decode_predictions function so I'm not sure how to use it with the response from parallel_model.predict. Any help or resources is appreciated, thanks.
the following site illustrates how to do that correctly link
Related
I am trying to build a transfer learning model to classify images. The images are a gray-scale (2D). previously I used image_dataset_from_directory method to read the images and there was no problem. However, I am trying to use a custom read function to have more control and access on the data such as knowing how many images in each class. When using this custom read function, I get an error (down below) while trying to train the model. I am not sure about what caused this error.
part1: reading the dataset
import numpy as np
import os
import tensorflow as tf
import cv2
from tensorflow import keras
# neural network
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers.experimental import preprocessing
IMG_WIDTH=160
IMG_HEIGHT=160
DATA_PATH = r"C:\Users\user\Documents\chest_xray"
TRAIN_DIR = os.path.join(DATA_PATH, 'train')
def create_dataset(img_folder):
img_data_array=[]
class_name=[]
for dir1 in os.listdir(img_folder):
for file in os.listdir(os.path.join(img_folder, dir1)):
image_path= os.path.join(img_folder, dir1, file)
image= cv2.imread( image_path, 0)
image=cv2.resize(image, (IMG_HEIGHT, IMG_WIDTH),interpolation = cv2.INTER_AREA)
image=np.array(image)
image = image.astype('float32')
image /= 255
img_data_array.append(image)
class_name.append(dir1)
return img_data_array, class_name
# extract the image array and class name
img_data, class_name =create_dataset(TRAIN_DIR)
target_dict={k: v for v, k in enumerate(np.unique(class_name))}
target_dict
target_val= [target_dict[class_name[i]] for i in range(len(class_name))]
this part will produce A list that has a size of 5232. inside the list there are numpy arrays of size 160X160 (float 32)
part 2: creating the model
def build_model():
inputs = tf.keras.Input(shape=(160, 160, 3))
x = Sequential(
[
preprocessing.RandomRotation(factor=0.15),
preprocessing.RandomTranslation(height_factor=0.1, width_factor=0.1),
preprocessing.RandomFlip(),
preprocessing.RandomContrast(factor=0.1),
],
name="img_augmentation",
)(inputs)
# x = img_augmentation(inputs)
model=tf.keras.applications.EfficientNetB7(include_top=False,
drop_connect_rate=0.4,
weights='imagenet',
input_tensor=x)
# Freeze the pretrained weights
model.trainable = False
# Rebuild top
x = tf.keras.layers.GlobalAveragePooling2D(name="avg_pool")(model.output)
x = tf.keras.layers.BatchNormalization()(x)
top_dropout_rate = 0.2
x = tf.keras.layers.Dropout(top_dropout_rate, name="top_dropout")(x)
outputs = tf.keras.layers.Dense(1, name="pred")(x)
# Compile
model = tf.keras.Model(inputs, outputs, name="EfficientNet")
optimizer = tf.keras.optimizers.Adam(learning_rate=1e-2)
model.compile(
optimizer=optimizer,
loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
metrics=["accuracy"]
)
return model
model = build_model()
part 3: train the model
history = model.fit(x=np.array(img_data), y=np.array(target_val), epochs=5)
the error I get:
ValueError: Shape must be rank 4 but is rank 3 for '{{node
EfficientNet/img_augmentation/random_rotation_1/transform/ImageProjectiveTransformV3}} =
ImageProjectiveTransformV3[dtype=DT_FLOAT, fill_mode="REFLECT", interpolation="BILINEAR"]
(IteratorGetNext, EfficientNet/img_augmentation/random_rotation_1/rotation_matrix/concat,
EfficientNet/img_augmentation/random_rotation_1/transform/strided_slice,
EfficientNet/img_augmentation/random_rotation_1/transform/fill_value)' with input shapes:
[?,160,160], [?,8], [2], [].
The problem in the code is that OpenCV reads the image in grayscale format, but the grayscale format of the image returned is not (160,160,1) but (160,160).
Because of this fact, the error is thrown.
I managed to replicate your problem by testing it locally.
Say we randomly train on 12 samples.
Possible input formats:
#This one works
1. history = model.fit(x=np.random.rand(12,160,160,3), y=np.array([1,1,1,1,1,1,0,0,0,0,0,0]), epochs=5,verbose=1) WORKS
#This one works
2. history = model.fit(x=np.random.rand(12,160,160,1), y=np.array([1,1,1,1,1,1,0,0,0,0,0,0]), epochs=5,verbose=1) WORKS
#This one fails
3. history = model.fit(x=np.random.rand(12,160,160), y=np.array([1,1,1,1,1,1,0,0,0,0,0,0]), epochs=5,verbose=1) FAILS
(1) and (2) work.
(3) fails, yielding:
ValueError: Shape must be rank 4 but is rank 3 for '{{node
EfficientNet/img_augmentation/random_rotation_4/transform/ImageProjectiveTransformV2}} = ImageProjectiveTransformV2[dtype=DT_FLOAT, fill_mode="REFLECT", interpolation="BILINEAR"](IteratorGetNext,
EfficientNet/img_augmentation/random_rotation_4/rotation_matrix/concat,
EfficientNet/img_augmentation/random_rotation_4/transform/strided_slice)'
with input shapes: [?,160,160], [?,8], [2].
Therefore, ensure that your data format is in the shape (160,160,1) or (160,160,3).
As an alternative, after you you read the image with OpenCV, you can use
image = np.expand_dims(image,axis=-1)
to programatically insert the last axis (the grayscale).
I built a network that attempts to predict raster images of surface temperatures.
The output of the network is a (1000, 1000) size array, representing a raster image. For training and testing these are compared to the real raster of their respective samples.
I understand how to add the training image to my TensorBoard callback but I'd like to also add the network's output image to the callback, so that I could compare them visually. Is this possible?
x = Input(shape = (2))
x = Dense(4)(x)
x = Reshape((2, 2))(x)
Where Reshape would be the last layer (or one before some deconvolution layer).
Depending on the tensorflow version you are using, I would have 2 different codes to suggest. I will assume you use > 2.0 and post the code I use for that version for image-to-image models. I basically initialize a callback with a noisy image (I am doing denoising but you can easily adapt to your problem), and the corresponding ground truth image. I then use the model to do the inference after each epoch.
"""Inspired by https://github.com/sicara/tf-explain/blob/master/tf_explain/callbacks/grad_cam.py"""
import numpy as np
import tensorflow as tf
from tensorflow.keras.callbacks import Callback
class TensorBoardImage(Callback):
def __init__(self, log_dir, image, noisy_image):
super().__init__()
self.log_dir = log_dir
self.image = image
self.noisy_image = noisy_image
def set_model(self, model):
self.model = model
self.writer = tf.summary.create_file_writer(self.log_dir, filename_suffix='images')
def on_train_begin(self, _):
self.write_image(self.image, 'Original Image', 0)
def on_train_end(self, _):
self.writer.close()
def write_image(self, image, tag, epoch):
image_to_write = np.copy(image)
image_to_write -= image_to_write.min()
image_to_write /= image_to_write.max()
with self.writer.as_default():
tf.summary.image(tag, image_to_write, step=epoch)
def on_epoch_end(self, epoch, logs={}):
denoised_image = self.model.predict_on_batch(self.noisy_image)
self.write_image(denoised_image, 'Denoised Image', epoch)
So typically you would use this the following way:
# define the model
model = Model(inputs, outputs)
# define the callback
image_tboard_cback = TensorBoardImage(
log_dir=log_dir + '/images',
image=val_gt[0:1],
noisy_image=val_noisy[0:1],
)
# fit the model
model.fit(
x,
y,
callbacks=[image_tboard_cback,],
)
If you use versions prior to 2.0 I can direct to this gist I wrote (which is a bit more intricate).
I am new to tensorflow and im still learning so I apologize if I am missing something obvious. So basically my problem is that I am trying to set up a simple image classifier with tensorflow in python, I figured out how to create my datasets and such but now I am just trying to get the training process going but the problem is that whenever I try I get this error
ValueError: Cannot reshape a tensor with 150528 elements to shape [224,150528] (33718272 elements) for 'dnn/input_from_feature_columns/input_layer/Image/Reshape' (op: 'Reshape') with input shapes: [224,224,3], [2] and with input tensors computed as partial shapes: input[1] = [224,150528].
I looked at some other posts I found here on stack overflow on this problem and they said that he was reshaping his data incorrectly and from what ive read from my error I have the same problem, the thing is I am using a premade estimator and I myself am not calling any reshaping functions in my code, the estimator is doing that for me I assume so how can I go about resolving this error? Thanks for any help here is my code
Training Code:
import tensorflow as tf
import cv2
import numpy as np
from DatasetCreator import DatasetCreator
trainingImagesPath = "TrainingImages"
#Loads the image data
def load_image(addr):
imageDimensions = (224, 224)
image = cv2.imread(addr)
#Resize the image to the size we need
image = cv2.resize(image, imageDimensions, interpolation=cv2.INTER_CUBIC)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)#Convert to RGB color space
image = image.astype(np.float32)
print(image.shape)
return image
#Load in the datasets
with tf.Graph().as_default() as graph:
dataCreator = DatasetCreator()
trainingDataset = dataCreator.generateDataset(trainingImagesPath)
#Create a training iterator for getting info from dataset
trainingIterator = trainingDataset.make_one_shot_iterator()
next_element = trainingIterator.get_next()
def train_input_fn():
with tf.Session(graph = graph) as sess:
features = sess.run(next_element)
#Get the image path
imagePath = str(features["ImagePath"])
imagePath = imagePath[2:len(imagePath)-1]
#Get the label
label = features["ImageLabel"]
image = load_image(imagePath)#Get image data
return {"Image": image, "Label": label}
featureColumns = [tf.feature_column.numeric_column("Image", [224, 224, 3]),
tf.feature_column.numeric_column("Label")]
estimator = tf.estimator.DNNClassifier(
model_dir = "Model",
feature_columns = featureColumns,
hidden_units = [1024, 512, 256],
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
)
print("Began training")
estimator.train(input_fn = train_input_fn, steps=1000)
Here is my code that creates my training dataset:
import tensorflow as tf
import cv2
from random import shuffle
import glob
import numpy as np
class DatasetCreator:
def __init__(self):
pass;
def generateDataset(self, trainingImagesPath):
addrs = glob.glob(trainingImagesPath + "/*.jpg")#Get list of paths of all the images in folder
#Label each address
labels = [0 if "car" in image else 1 for image in addrs]#Compile list of labels
# Divide the hata into 60% train, 20% validation, and 20% test
train_addrs = addrs[0:int(0.6*len(addrs))]
train_labels = labels[0:int(0.6*len(labels))]
val_addrs = addrs[int(0.6*len(addrs)):int(0.8*len(addrs))]
val_labels = labels[int(0.6*len(addrs)):int(0.8*len(addrs))]
test_addrs = addrs[int(0.8*len(addrs)):]
test_labels = labels[int(0.8*len(labels)):]
#Create dataset
dataset = tf.data.Dataset.from_tensor_slices(
{"ImagePath": train_addrs,
"ImageLabel": train_labels})
return dataset;
I am rather new to Tensorflow, and has been trying to pick up the basics by reading through the guides and documentation on tensorflow.org
I have learnt the basics of how to use the tf.data and tf.estimator APIs and is trying to get them to work together on a basic classification model for MNIST.
I am using this script to load MNIST: https://github.com/tensorflow/models/blob/master/official/mnist/dataset.py
I made modifications to the dataset function to return a feature dictionary rather than vector:
def dataset(directory, images_file, labels_file):
"""Download and parse MNIST dataset."""
images_file = download(directory, images_file)
labels_file = download(directory, labels_file)
check_image_file_header(images_file)
check_labels_file_header(labels_file)
def decode_image(image):
# Normalize from [0, 255] to [0.0, 1.0]
image = tf.decode_raw(image, tf.uint8)
image = tf.cast(image, tf.float32)
image = tf.reshape(image, [784])
return image / 255.0
def decode_label(label):
label = tf.decode_raw(label, tf.uint8) # tf.string -> [tf.uint8]
label = tf.reshape(label, []) # label is a scalar
return tf.to_int32(label)
images = tf.data.FixedLengthRecordDataset(
images_file, 28 * 28, header_bytes=16).map(decode_image)
labels = tf.data.FixedLengthRecordDataset(
labels_file, 1, header_bytes=8).map(decode_label)
return tf.data.Dataset.zip(({"image":images}, labels))
My MNIST classifier script using the premade estimator in tf is as follows:
import tensorflow as tf
import dataset
fc = [tf.feature_column.numeric_column("image", shape=784)]
mnist_classifier = tf.estimator.DNNClassifier(
hidden_units=[512,512],
feature_columns=fc,
model_dir="models/mnist/dnn",
n_classes=10)
def input_fn(train=False, batch_size=None):
if train:
ds = mnist.train("MNIST-data")
ds = ds.shuffle(1000).repeat().batch(batch_size)
else:
ds = mnist.test("MNIST-data")
return ds
mnist_classifier.train(
input_fn=lambda:input_fn(True, 32),
steps=10000)
eval_results = mnist_classifier.evaluate(input_fn=lambda:input_fn())
The classifier doesn't crash on training, but on evaluate, I faced the following traceback:
ValueError: Cannot reshape a tensor with 784 elements to shape
[784,784] (614656 elements) for
'dnn/input_from_feature_columns/input_layer/image/Reshape' (op:
'Reshape') with input shapes: [784,1], [2] and with input tensors
computed as partial shapes: input[1] = [784,784].
What could be causing the issue here?
I have tried printing the output shapes and types of both train and test datasets, and they are exactly the same.
I have also tried viewing the model on tensorboard, and only the projector tab is available, no scalars or graphs tab.
Thanks!
PS: Any links to TF tutorials using the Datasets and Estimators APIs will be great too.
I have downloaded a tensorflow checkpoint model named inception_resnet_v2_2016_08_30.ckpt.
Do I need to create a graph (with all the variables) that were used when this checkpoint was created?
How do I make use of this model?
First of you have get the network architecture in memory. You can get the network architecture from here
Once you have this program with you, use the following approach to use the model:
from inception_resnet_v2 import inception_resnet_v2, inception_resnet_v2_arg_scope
height = 299
width = 299
channels = 3
X = tf.placeholder(tf.float32, shape=[None, height, width, channels])
with slim.arg_scope(inception_resnet_v2_arg_scope()):
logits, end_points = inception_resnet_v2(X, num_classes=1001,is_training=False)
With this you have all the network in memory, Now you can initialize the network with checkpoint file(ckpt) by using tf.train.saver:
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess, "/home/pramod/Downloads/inception_resnet_v2_2016_08_30.ckpt")
If you want to do bottle feature extraction, its simple like lets say you want to get features from last layer, then simply you have to declare predictions = end_points["Logits"] If you want to get it for other intermediate layer, you can get those names from the above program inception_resnet_v2.py
After that you can call: output = sess.run(predictions, feed_dict={X:batch_images})
Do I need to create a graph (with all the variables) that were used when this checkpoint was created?
No, you don't.
As for how to use checkpoint file (cpkt file)
1.This article (TensorFlow-Slim image classification library) tells you how to train your model from scratch
2.The following is an example code from google blog
import numpy as np
import os
import tensorflow as tf
import urllib2
from datasets import imagenet
from nets import inception
from preprocessing import inception_preprocessing
slim = tf.contrib.slim
batch_size = 3
image_size = inception.inception_v3.default_image_size
checkpoints_dir = '/root/code/model'
checkpoints_filename = 'inception_resnet_v2_2016_08_30.ckpt'
model_name = 'InceptionResnetV2'
sess = tf.InteractiveSession()
graph = tf.Graph()
graph.as_default()
def classify_from_url(url):
image_string = urllib2.urlopen(url).read()
image = tf.image.decode_jpeg(image_string, channels=3)
processed_image = inception_preprocessing.preprocess_image(image, image_size, image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
logits, _ = inception.inception_resnet_v2(processed_images, num_classes=1001, is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, checkpoints_filename),
slim.get_model_variables(model_name))
init_fn(sess)
np_image, probabilities = sess.run([image, probabilities])
probabilities = probabilities[0, 0:]
sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x:x[1])]
plt.figure()
plt.imshow(np_image.astype(np.uint8))
plt.axis('off')
plt.show()
names = imagenet.create_readable_names_for_imagenet_labels()
for i in range(5):
index = sorted_inds[i]
print('Probability %0.2f%% => [%s]' % (probabilities[index], names[index]))
Another way of loading a pre-trained Imagenet model is
ResNet50
import tensorflow as tf
from tensorflow.keras.applications.resnet50 import ResNet50
model = ResNet50()
model.summary()
InceptionV3
iport tensorflow as tf
from tensorflow.keras.applications.inception_v3 import InceptionV3
model = InceptionV3()
model.summary()
You can check a detailed explanation related to this here