def predict(weights_path, image_path):
model = Net.build(32, 32, 3, weights_path)
image = load_image(image_path)
class_ = model.predict(image)
output_indice = -1
# get class index having maximum predicted score
for i in range(36):
if (i == 0):
max = class_[0][i]
output_indice = 0
else:
if (class_[0][i] > max):
max = class_[0][i]
output_indice = i
# append 26 characters (A to Z) to list characters
characters = []
for i in range(65, 65 + 26):
characters.append(chr(i))
if (output_indice > 9):
final_result = characters[(output_indice - 9) - 1]
print("Predicted: ", final_result)
else:
print("No result can be fulfilled")
def predict_frames():
"""
Loads pretrained CNN to predict on all frame images
predictions: nparray with class prediction on all images
filenames: nparray of all frame filenames
"""
frames, filenames = get_data()
model = Net.build(width=imageSize, height=imageSize, depth=3)
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.load_weights('trained_weights_2.h5')
predicted_classes = model.predict(frames)
predictions = np.argmax(predicted_classes, axis=1)
#for i in range(len(predictions)):
#print('Predicted class: {} for image: {} with confidence: {}'.format(map_characters[predictions[i]], filenames[i], np.amax(predicted_classes[i])*100))
return predictions, filenames
def predict(weights_path, image_path):
'''
Function: loads a trained model and predicts the class of given image
Input: weights_path (.h5 file, prefer adding absolute path)
image_path (image to predict, prefer adding absolute path)
Returns: none
'''
model = Net.build(32, 32, 3, weights_path)
image = load_image(image_path, show=True) # load image, rescale to 0 to 1
class_ = model.predict(
image) # predict the output, returns 36 length array
print("Detected: ", class_[0]) # print what is predicted
output_indice = -1 # set it initially to -1
# get class index having maximum predicted score
for i in range(36):
if (i == 0):
max = class_[0][i]
output_indice = 0
else:
if (class_[0][i] > max):
max = class_[0][i]
output_indice = i
# append 26 characters (A to Z) to list characters
characters = []
for i in range(65, 65 + 26):
characters.append(chr(i))
# if output indice > 9 (means characters)
if (output_indice > 9):
final_result = characters[(output_indice - 9) - 1]
print("Predicted: ", final_result)
print("value: ", max) # print predicted score
# else it's a digit, print directly
else:
print("Predicted: ", output_indice)
print("value: ", max) # print it's predicted score
def predict(weights_path, image_path):
'''
Function: loads a trained model and predicts the class of given image
Input: weights_path (.h5 file, prefer adding absolute path)
image_path (image to predict, prefer adding absolute path)
Returns: none
'''
model = Net.build(32, 32, 3, weights_path)
image = load_image(image_path, show=True) # load image, rescale to 0 to 1
class_ = model.predict(image) # predict the output, returns 36 length array
print("Detected: ", class_[0]) # print what is predicted
output_indice = -1 # set it initially to -1
# get class index having maximum predicted score
for i in range(36):
if(i == 0):
max = class_[0][i]
output_indice = 0
else:
if(class_[0][i] > max):
max = class_[0][i]
output_indice = i
# append 26 characters (A to Z) to list characters
characters = []
for i in range(65, 65+26):
characters.append(chr(i))
# if output indice > 9 (means characters)
if(output_indice > 9):
final_result = characters[(output_indice - 9) - 1]
print("Predicted: ", final_result)
print("value: ", max) # print predicted score
# else it's a digit, print directly
else:
print("Predicted: ", output_indice)
print("value: ", max) # print it's predicted score
# Dimensions of our images
img_width, img_height = 64, 64
# 3 channel image
no_of_channels = 3
# Training variables
epochs = 6
batch_size = 64
# Train data Directory
train_data_dir = 'data/train/'
# Load model from Net
model = Net.build(width=img_width, height=img_height, depth=no_of_channels)
print('--------building done--------')
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
print('--------compiling done--------')
def preprocess_image(image):
'''Function that will be implied on each input. The function
will run after the image is resized and augmented.
The function should take one argument: one image (Numpy tensor
with rank 3), and should output a Numpy tensor with the same
shape.'''
sobely = cv2.Sobel(image, cv2.CV_64F, 0, 1, ksize=5)
return sobely
# Dimensions of our images
img_width, img_height = 32, 32
# 3 channel image
no_of_channels = 3
# train data Directory
train_data_dir = 'train/'
# test data Directory
validation_data_dir = 'test/'
epochs = 80
batch_size = 32
#initialize model
model = Net.build(width = img_width, height = img_height, depth = no_of_channels)
print('building done')
# Compile model
rms = optimizers.RMSprop(lr=0.001, rho=0.9, epsilon=None, decay=0.0)
print('optimizing done')
model.compile(loss='categorical_crossentropy',
optimizer=rms,
metrics=['accuracy'])
print('compiling')
# this is the augmentation configuration used for training
# horizontal_flip = False, as we need to retain Characters
train_datagen = ImageDataGenerator(
featurewise_center=True,
from keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
from keras import optimizers
from net import Net # creating modelNameName
wdthIm, hghtIm = 32, 32 # set image size
channelNo = 3 # set image number
data_dir_train = 'test_together/'
data_dirc_validation = 'test_together/'
epochNo = 120
batchSize = 52
modelName = Net.build(width=wdthIm, height=hghtIm,
depth=channelNo) #modelName name
print('building done!!')
Rms = optimizers.Rmsprop(lr=0.001, rho=0.9, epsilon=None,
decay=0.0) #compiling model
print('optimizing done!!')
modelName.compile(loss='categorical_crossentropy',
optimizer=Rms,
metrics=['accuracy'])
print('compiling.....')
train_datagenerator = ImageDataGenerator(
featurewise_centering=True,
featurewise_std_normaliztn=True,
shear_ranges=0.1,
zoom_ranges=0.1,
rotation_ranges=5,
label,
test_size=0.25,
random_state=30)
classes = len(labels)
trainY = to_categorical(trainY, num_classes=classes)
testY = to_categorical(testY, num_classes=classes)
aug = ImageDataGenerator(rotation_range=30,
width_shift_range=0.1,
height_shift_range=0.1,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
fill_mode="nearest")
print("[INFO] Compiling model...")
model = Net.build(width=28, height=28, depth=3, classes=classes)
opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
model.compile(loss="binary_crossentropy", optimizer=opt, metrics=["accuracy"])
print("[INFO] Training model...")
H = model.fit_generator(aug.flow(trainX, trainY, batch_size=BATCH_SIZE),
validation_data=(testX, testY),
steps_per_epoch=len(trainX) // BATCH_SIZE,
epochs=EPOCHS,
verbose=1)
model.save(args["model"])
print("[INFO] Model Saved...")