def cache_images_dir(dir, max_n=1000, replace=False):
# Inception
inception.maybe_download()
model = inception.Inception()
# Storage
file_path_cache = os.path.join(dir + '/images_features.pkl')
if replace:
os.remove(file_path_cache)
print("Processing Inception transfer-values...")
dir_im = dir + '/pics'
n_total_images = sum([len(files) for r, d, files in os.walk(dir_im)])
n_total_images = min([max_n, n_total_images])
print('Fetching %d images in %s ...' % (n_total_images, dir_im))
images = np.zeros((n_total_images, 192, 256, 3), dtype=np.float32)
id = []
index = 0
n_err = 0
for d in os.listdir(dir_im):
if index >= max_n:
break
d = dir_im + '/' + d
for image_name in os.listdir(d):
if index >= max_n:
break
image_path = d + '/' + image_name
try:
image_data = (misc.imread(image_path)[:, :, :3]).astype(
np.float32)
images[
index, :, :, :] = image_data # (n, height, width, channels)
id.append(os.path.splitext(image_name)[0])
index += 1
except OSError as err:
print(err)
n_err += 1
if n_err > 0:
images = np.delete(images, range(n_total_images - n_err,
n_total_images), 0)
id = np.array(id)
transfer_values = inception.transfer_values_cache(
cache_path=file_path_cache, images=images, model=model)
return transfer_values, id
def test(queries=list(), location='./test'):
"""
Test your system with the input. For each input, generate a list of IDs that is returned
:param queries: list of image-IDs. Each element is assumed to be an entry in the test set. Hence, the image
with id <id> is located on my computer at './test/pics/<id>.jpg'. Make sure this is the file you work with...
:param location: The location of the test data folder hierarchy
:return: a dictionary with keys equal to the images in the queries - list, and values a list of image-IDs
retrieved for that input
"""
# # ##### The following is an example implementation -- that would lead to 0 points in the evaluation :-)
# my_return_dict = {}
#
# # Load the dictionary with all training files. This is just to get a hold of which
# # IDs are there; will choose randomly among them
# training_labels = pickle.load(open('./train/pickle/combined.pickle', 'rb'))
# training_labels = list(training_labels.keys())
#
# for query in queries:
#
# # This is the image. Just opening if here for the fun of it; not used later
# image = Image.open(location + '/pics/' + query + '.jpg')
# image.show()
#
# # Generate a random list of 50 entries
# cluster = [training_labels[random.randint(0, len(training_labels) - 1)] for idx in range(50)]
# my_return_dict[query] = cluster
my_return_dict = {}
# Inception
inception.maybe_download()
model = inception.Inception()
for query in queries:
# Data
image_path = location + '/pics/' + query + '.jpg'
image_data = (misc.imread(image_path)[:, 0:192, :3]).astype(np.float32)
image_tranfer_values = model.transfer_values(image_path, image_data)
# Inference
my_return_dict[query] = infere(image_tranfer_values)
return my_return_dict
def main():
# command line arguments
img_dir = sys.argv[1]
save_path = sys.argv[2]
# geting list of images from specified dir
imgs = get_file_list(img_dir)
print("Number of images: ", len(imgs))
# loading Inception
inception.maybe_download()
# creating an Inception instance
model = inception.Inception()
write_output_to_pickle(imgs, img_dir, model, save_path=save_path)
model.close()
def load_inception_model():
# make directory if not exist
if not os.path.isdir("data"):
os.mkdir("data")
if not os.path.isdir("data/CIFAR-10"):
os.mkdir("data/CIFAR-10")
if not os.path.isdir("inception"):
os.mkdir("inception")
if not os.path.isdir("img"):
os.mkdir("img")
if not os.path.isdir("graphs"):
os.mkdir("graphs")
# load inception model
inception.maybe_download(
) # download inception data (85MB) if not exist in inception directory
model = inception.Inception() # load inception model
return model
def main():
img_path = sys.argv[1]
data, img_lst = load_data_np("../data/transfer_layer")
t = build_Index(data, len(data[0]))
save_index(t, path)
n = gc.collect()
inception.maybe_download()
incept = inception.Inception()
vector = get_tl_vector(incept, img_path)
x = t.get_nns_by_vector(vector, n=50)
print(x)
def test_dataset(pickle_f):
inception.maybe_download()
model = inception.Inception()
images, labels = pickle.load(
open( expanduser("~/adversary/data/pickles/" + pickle_f), "rb"))
pred = inception.process_images(fn=model.classify, images=images)
#picks the category with the highest score
labels_true = numpy.argmax(labels, axis=1)
labels_pred = numpy.argmax(pred, axis=1)
conf_matrix = confusion_matrix(labels_true, labels_pred)
accuracy = accuracy_score(labels_true, labels_pred)
f = open(expanduser("~/adversary/data/results/" + pickle_f), 'w')
f.write("Accuracy = " + str(accuracy) + '\n') # python will convert \n to os.linesep
f.write("Confusion Matrix: " + str(conf_matrix) + '\n')
f.close()
model.close()
from os.path import expanduser
import sys
sys.path.insert(0, expanduser('~/adversary/src/models'))
sys.path.insert(0, expanduser('~/adversary/src/utils/Hvass_Lab'))
# Functions and classes for loading and using the Inception model.
import inception
# specify the location where we should keep all the files
# associated with the inception model
inception.data_dir = expanduser("~/adversary/src/models/inception")
#Download the data for the Inception model if it doesn't already
# exist in the directory. It is 85 MB.
inception.maybe_download()
#Load the Inception model so it is ready for classifying images.
model = inception.Inception()
#Get a reference to the input tensor for the Inception model.
resized_image = model.resized_image
#Get a reference to the output of the softmax-classifier for the Inception model.
y_pred = model.y_pred
#Get a reference to the unscaled output of the softmax-classifier for the Inception
# model. These are often called 'logits'. The logits are necessary because we will
# add a new loss-function to the graph, which requires these unscaled outputs.
y_logits = model.y_logits
def main(splitnum):
test, train, val = transfer.preprocessing(
"/home/runefeather/Desktop/Classwork/AI/Project/breakhissplits_v2/train_val_test_60_12_28/"
)
transfer.split(test, train, val, str(splitnum))
tumordata.add_data_path(splitnum)
tumordata.start()
print(tumordata.data_path)
class_names = tumordata.load_class_names()
images_train, cls_train, labels_train = tumordata.load_training_data()
images_test, cls_test, labels_test = tumordata.load_testing_data()
print("Size of:")
print("- Training-set:\t\t{}".format(len(images_train)))
print("- Test-set:\t\t{}".format(len(images_test)))
# inception dir
inception.data_dir = 'inception/'
# download the model
inception.maybe_download()
# load model
model = inception.Inception()
# caches for training and test sets
file_path_cache_train = os.path.join(tumordata.data_path,
'inception_tumordata_train.pkl')
file_path_cache_test = os.path.join(tumordata.data_path,
'inception_tumordata_test.pkl')
print("Processing Inception transfer-values for training-images ...")
# If transfer-values have already been calculated then reload them,
# otherwise calculate them and save them to a cache-file.
transfer_values_train = transfer_values_cache(
cache_path=file_path_cache_train, images=images_train, model=model)
print("Processing Inception transfer-values for test-images ...")
# If transfer-values have already been calculated then reload them,
# otherwise calculate them and save them to a cache-file.
transfer_values_test = transfer_values_cache(
cache_path=file_path_cache_test, images=images_test, model=model)
transfer_len = model.transfer_len
x = tf.placeholder(tf.float32, shape=[None, transfer_len], name='x')
y_true = tf.placeholder(tf.float32,
shape=[None, num_classes],
name='y_true')
y_true_cls = tf.argmax(y_true, dimension=1)
# Wrap the transfer-values as a Pretty Tensor object.
x_pretty = pt.wrap(x)
with pt.defaults_scope(activation_fn=tf.nn.relu):
y_pred, loss = x_pretty.\
fully_connected(size=1024, name='layer_fc1').\
softmax_classifier(num_classes=num_classes, labels=y_true)
global_step = tf.Variable(initial_value=0,
name='global_step',
trainable=False)
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(
loss, global_step)
y_pred_cls = tf.argmax(y_pred, dimension=1)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
session = tf.Session()
session.run(tf.global_variables_initializer())
print_test_accuracy(session, x, y_true, y_pred_cls, transfer_values_test,
labels_test, cls_test)
session = optimize(5000, session, x, y_true, global_step, optimizer,
accuracy, transfer_values_train, labels_train)
print_test_accuracy(session, x, y_true, y_pred_cls, transfer_values_test,
labels_test, cls_test)
model.close()
session.close()
from reverse_img_query import load_data_np, \
build_Index, \
get_tl_vector, \
get_ol_vector
from inception import Inception, maybe_download
import gc
from pathing_utils import path_to_image_frontend, \
path_to_static, \
path_to_images_folder_absolute, \
image_name_from_path,\
path_to_uploads
from utils import image_from_base64str
maybe_download()
inception_layer_path = path_to_static() + "inception_output_layer2"
inverted_index_path = path_to_static() + "inverted_index"
vocab_path = path_to_static() + "vocab.csv"
word2vec_vocab_path = path_to_static() + "word2vecvocab.csv"
word_vec_path = path_to_static() + "GoogleNews-vectors-negative300.bin.gz"
print("READ inception_layer_path")
inverted_index = pd.read_pickle(inverted_index_path)
df_in = pd.read_pickle(inception_layer_path)
df_in.columns = ['img', 'output_layer', 'scores']
# print("DROP column - output_layer")
df_in.drop('output_layer', axis=1, inplace=True)
# print(df_in.head())
known_words = defaultdict(list)
annoy_index = None
inception_object = None
def Appliquer_inception(image_path): inception.maybe_download() model = inception.Inception() resized_image = model.get_resized_image(image_path=image_path) classify(image_path="images/Velo9.jpg")
def main(splitnum, finalimgpath):
# print stuff
print("=========================================")
print(splitnum)
train_batch_size = 64
def random_batch():
# Number of images (transfer-values) in the training-set.
num_images = len(transfer_values_train)
# Create a random index.
idx = np.random.choice(num_images,
size=train_batch_size,
replace=False)
# Use the random index to select random x and y-values.
# We use the transfer-values instead of images as x-values.
x_batch = transfer_values_train[idx]
y_batch = labels_train[idx]
return x_batch, y_batch
def optimize(num_iterations):
# Start-time used for printing time-usage below.
start_time = time.time()
# Else, save for the first time
saver = tf.train.Saver(tf.all_variables(), max_to_keep=100)
session_list = []
test_acc = []
for i in range(num_iterations):
# Get a batch of training examples.
# x_batch now holds a batch of images (transfer-values) and
# y_true_batch are the true labels for those images.
x_batch, y_true_batch = random_batch()
# Put the batch into a dict with the proper names
# for placeholder variables in the TensorFlow graph.
feed_dict_train = {x: x_batch, y_true: y_true_batch}
# Run the optimizer using this batch of training data.
# TensorFlow assigns the variables in feed_dict_train
# to the placeholder variables and then runs the optimizer.
# We also want to retrieve the global_step counter.
i_global, _ = session.run([global_step, optimizer],
feed_dict=feed_dict_train)
# Print status to screen every 100 iterations (and last).
if (i_global % 100 == 0) or (i == num_iterations - 1):
savepath = saver.save(session,
'checkpoints\\split1\\model',
global_step=i_global)
session_list.append(savepath)
# Calculate the accuracy on the training-batch.
batch_acc = session.run(accuracy, feed_dict=feed_dict_train)
# Test accuracy with session
correct, cls_pred = predict_cls_test()
acc, num_correct = classification_accuracy(correct)
# Print status.
# msg = "Global Step: {0:>6}, Training Batch Accuracy: {1:>6.1%}"
# print(msg.format(i_global, batch_acc))
# print("Testing Accuracy: ", round(acc*100, 2))
# save test accuracy
test_acc.append(round(acc * 100, 2))
# print("========================================================")
# Ending time.
end_time = time.time()
# Difference between start and end-times.
time_dif = end_time - start_time
# Print the time-usage.
print("Time usage: " + str(timedelta(seconds=int(round(time_dif)))))
max_acc = max(test_acc)
print("MAX: ", max_acc)
# print(list(test_acc.values()).index(max_acc))
print(test_acc.index(max_acc))
# print(mydict.values().index(max(test_acc.values()))) #
pth = session_list[test_acc.index(max_acc)]
saver.restore(session, pth)
return
def plot_example_errors(cls_pred, correct):
# This function is called from print_test_accuracy() below.
# cls_pred is an array of the predicted class-number for
# all images in the test-set.
# correct is a boolean array whether the predicted class
# is equal to the true class for each image in the test-set.
# Negate the boolean array.
incorrect = (correct == False)
# Get the images from the test-set that have been
# incorrectly classified.
images = images_test[incorrect]
# Get the predicted classes for those images.
cls_pred = cls_pred[incorrect]
# Get the true classes for those images.
cls_true = cls_test[incorrect]
n = min(9, len(images))
# Plot the first n images.
plot_images(images=images[0:n],
cls_true=cls_true[0:n],
cls_pred=cls_pred[0:n])
def plot_confusion_matrix(cls_pred):
# This is called from print_test_accuracy() below.
# cls_pred is an array of the predicted class-number for
# all images in the test-set.
# Get the confusion matrix using sklearn.
cm = confusion_matrix(
y_true=cls_test, # True class for test-set.
y_pred=cls_pred) # Predicted class.
# Print the confusion matrix as text.
for i in range(num_classes):
# Append the class-name to each line.
class_name = "({}) {}".format(i, class_names[i])
print(cm[i, :], class_name)
# Print the class-numbers for easy reference.
class_numbers = [" ({0})".format(i) for i in range(num_classes)]
print("".join(class_numbers))
# Split the data-set in batches of this size to limit RAM usage.
batch_size = 256
def predict_cls(transfer_values, labels, cls_true):
# Number of images.
num_images = len(transfer_values)
# Allocate an array for the predicted classes which
# will be calculated in batches and filled into this array.
cls_pred = np.zeros(shape=num_images, dtype=np.int)
# Now calculate the predicted classes for the batches.
# We will just iterate through all the batches.
# The starting index for the next batch is denoted i.
i = 0
while i < num_images:
# The ending index for the next batch is denoted j.
j = min(i + batch_size, num_images)
# Create a feed-dict with the images and labels
# between index i and j.
feed_dict = {x: transfer_values[i:j], y_true: labels[i:j]}
# Calculate the predicted class using TensorFlow.
cls_pred[i:j] = session.run(y_pred_cls, feed_dict=feed_dict)
# Set the start-index for the next batch to the
# end-index of the current batch.
i = j
# Create a boolean array whether each image is correctly classified.
correct = (cls_true == cls_pred)
return correct, cls_pred
def predict_one_image(imgarr):
# Number of images.
num_images = 1
label = np.zeros(shape=[0, 2], dtype=np.int)
# Allocate an array for the predicted classes which
# will be calculated in batches and filled into this array.
cls_pred = np.zeros(shape=num_images, dtype=np.int)
feed_dict = {x: imgarr, y_true: label}
cls_pred = session.run(y_pred_cls, feed_dict=feed_dict)
return cls_pred
def predict_cls_test():
return predict_cls(transfer_values=transfer_values_test,
labels=labels_test,
cls_true=cls_test)
def classification_accuracy(correct):
# When averaging a boolean array, False means 0 and True means 1.
# So we are calculating: number of True / len(correct) which is
# the same as the classification accuracy.
# Return the classification accuracy
# and the number of correct classifications.
return correct.mean(), correct.sum()
def print_test_accuracy(show_example_errors=False,
show_confusion_matrix=False):
# For all the images in the test-set,
# calculate the predicted classes and whether they are correct.
correct, cls_pred = predict_cls_test()
# Classification accuracy and the number of correct classifications.
acc, num_correct = classification_accuracy(correct)
# Number of images being classified.
num_images = len(correct)
# Print the accuracy.
msg = "Accuracy on Test-Set: {0:.1%} ({1} / {2})"
print(msg.format(acc, num_correct, num_images))
# Plot some examples of mis-classifications, if desired.
if show_example_errors:
print("Example errors:")
plot_example_errors(cls_pred=cls_pred, correct=correct)
# Plot the confusion matrix, if desired.
if show_confusion_matrix:
print("Confusion Matrix:")
plot_confusion_matrix(cls_pred=cls_pred)
# =========================================================================================
# THIS IS WHERE EVERYTHING COMES TOGETHER
# =========================================================================================
test, train, val = transfer.preprocessing(
"D:\\AI Stuff\\aiproject-inception-master\\breakhissplits_v2\\train_val_test_60_12_28\\"
)
transfer.split(test, train, val, str(splitnum))
tumordata.add_data_path(splitnum)
tumordata.start()
print(tumordata.data_path)
class_names = tumordata.load_class_names()
images_train, cls_train, labels_train = tumordata.load_training_data()
images_test, cls_test, labels_test = tumordata.load_testing_data()
print("Size of:")
print("- Training-set:\t\t{}".format(len(images_train)))
print("- Test-set:\t\t{}".format(len(images_test)))
# Image to predict on
img = Image.open(finalimgpath)
imgarr = []
imgarr.append(np.array(img))
# inception dir
inception.data_dir = 'inception/'
# download the model
inception.maybe_download()
# load model
model = inception.Inception()
# caches for training and test sets
file_path_cache_train = os.path.join(tumordata.data_path,
'inception_tumordata_train.pkl')
file_path_cache_test = os.path.join(tumordata.data_path,
'inception_tumordata_test.pkl')
file_path_cache_single_test = os.path.join(
tumordata.data_path, 'inception_tumordata_single_test.pkl')
print("Processing Inception transfer-values for training-images ...")
# If transfer-values have already been calculated then reload them,
# otherwise calculate them and save them to a cache-file.
transfer_values_train = transfer_values_cache(
cache_path=file_path_cache_train, images=images_train, model=model)
print("Processing Inception transfer-values for test-images ...")
# If transfer-values have already been calculated then reload them,
# otherwise calculate them and save them to a cache-file.
transfer_values_test = transfer_values_cache(
cache_path=file_path_cache_test, images=images_test, model=model)
transfer_values_single_test = transfer_values_cache(
cache_path=file_path_cache_single_test, images=imgarr, model=model)
# print("TRANSFER VALUES TEST: ", transfer_values_test)
transfer_len = model.transfer_len
x = tf.placeholder(tf.float32, shape=[None, transfer_len], name='x')
y_true = tf.placeholder(tf.float32,
shape=[None, num_classes],
name='y_true')
y_true_cls = tf.argmax(y_true, dimension=1)
# x_one = tf.placeholder(tf.float32, shape=[len(imgarr), len(imgarr[0]), 3], name='x_one')
# y_true_one = tf.placeholder(tf.float32, shape=1, name='y_true_one')
# y_true_cls_one = tf.argmax(y_true_one, dimension=1)
# Wrap the transfer-values as a Pretty Tensor object.
x_pretty = pt.wrap(x)
with pt.defaults_scope(activation_fn=tf.nn.relu):
y_pred, loss = x_pretty.\
fully_connected(size=1024, name='layer_fc1').\
softmax_classifier(num_classes=num_classes, labels=y_true)
global_step = tf.Variable(initial_value=0,
name='global_step',
trainable=False)
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(
loss, global_step)
y_pred_cls = tf.argmax(y_pred, dimension=1)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
session = tf.Session()
session.run(tf.global_variables_initializer())
print_test_accuracy(show_example_errors=False, show_confusion_matrix=False)
optimize(1000)
print_test_accuracy(show_example_errors=False, show_confusion_matrix=False)
correct, cls_pred = predict_cls_test()
acc, num_correct = classification_accuracy(correct)
# print("acc, num correct: ", acc, num_correct)
cls_pred = predict_one_image(transfer_values_single_test)
# print("PREDICTION")
# print(cls_pred)
print(">>>>>>>>>>>><<<<<<<<<<<<<<<<")
# prediction = model.classify(finalimgpath)
return acc, cls_pred
def setup():
cifar10.maybe_download_and_extract()
inception.maybe_download()