Learnt from Jerry Kurata on Pluralsight, I'm trying to recognize birds:
my dataset structure is:
My model training code is:
import glob
import matplotlib.pyplot as plt
from keras import backend as K
import tensorflow as tf
with K.tf.device("/device:GPU:0"):
config = tf.ConfigProto(intra_op_parallelism_threads=4,
inter_op_parallelism_threads=4, allow_soft_placement=True,
device_count = {'CPU' : 1, 'GPU' : 1})
session = tf.Session(config=config)
K.set_session(session)
from keras.callbacks import EarlyStopping
from keras.applications.inception_v3 import InceptionV3, preprocess_input
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import SGD
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
# "/device:GPU:0"
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
def get_num_files(path):
if not os.path.exists(path):
return 0
return sum([len(files) for r, d, files in os.walk(path)])
def get_num_subfolders(path):
if not os.path.exists(path):
return 0
return sum([len(d) for r, d, files in os.walk(path)])
def create_img_generator():
return ImageDataGenerator(
preprocessing_function=preprocess_input,
rotation_range=30,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True
)
Image_width, Image_height = 299, 299
Training_Epochs = 1
Batch_Size = 32
Number_FC_Neurons = 1024
train_dir = '.../birds/train'
validate_dir = '.../birds/validation'
num_train_samples = get_num_files(train_dir)
num_classes = get_num_subfolders(train_dir)
num_validate_samples = get_num_files(validate_dir)
num_epoch = Training_Epochs
batch_size = Batch_Size
train_image_gen = create_img_generator()
test_image_gen = create_img_generator()
train_generator = train_image_gen.flow_from_directory(
train_dir,
target_size=(Image_width, Image_height),
batch_size = batch_size,
seed = 42
)
validation_generator = test_image_gen.flow_from_directory(
validate_dir,
target_size=(Image_width, Image_height),
batch_size=batch_size,
seed=42
)
Inceptionv3_model = InceptionV3(weights='imagenet', include_top=False)
print('Inception v3 model without last FC loaded')
x = Inceptionv3_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(Number_FC_Neurons, activation='relu')(x)
predictions = Dense(num_classes, activation='softmax')(x)
model = Model(inputs=Inceptionv3_model.input, outputs=predictions)
print(model.summary())
print('\nFine tuning existing model')
Layers_To_Freeze = 172
for layer in model.layers[:Layers_To_Freeze]:
layer.trainable = False
for layer in model.layers[Layers_To_Freeze:]:
layer.trainable = True
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='binary_crossentropy', metrics=['accuracy'])
cbk_early_stopping = EarlyStopping(monitor='val_acc', mode='max')
history_transfer_learning = model.fit_generator(
train_generator,
steps_per_epoch = num_train_samples,
epochs=num_epoch,
validation_data=validation_generator,
validation_steps = num_validate_samples,
class_weight='auto',
callbacks=[cbk_early_stopping]
)
model.save('incepv3_transfer.h5', overwrite=True, include_optimizer=True)
My detector is
from keras.models import load_model
from keras.optimizers import SGD
from keras.preprocessing import image
from keras.applications.inception_v3 import preprocess_input
import matplotlib.pyplot as plt
import numpy as np
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
class Detector:
def __init__(self, model_path):
self.model = load_model(model_path)
print('input shape') # output is always (None, None, None, 3), this should be wrong
print(self.model.layers[0].input_shape)
# self.model.summary()
# self.model.compile(loss='binary_crossentropy', optimizer=SGD(lr=0.0001, momentum=0.9), metrics=['accuracy'])
def preprocess_input(self, x):
y = np.copy(x)
y /= 255.
y -= 0.5
y *= 2.
return y
def load_image(self, img_path, show=False):
img = image.load_img(img_path, target_size=(299,299))
img_tensor = image.img_to_array(img) # (height, width, channels)
img_tensor = np.expand_dims(img, axis=0) # (1, height, width, channels), add a dimension because the model expects this shape: (batch_size, height, width, channels)
# img_tensor /= 255. # imshow expects values in the range [0, 1]
img_tensor = preprocess_input(img_tensor)
if show:
plt.imshow(img_tensor[0])
plt.axis('off')
plt.show()
return img_tensor
def detect(self, img_path):
img = self.load_image(img_path, True)
classes = self.model.predict(img)
return classes
from this link
And here is how I use them to predict whether an image has a bird or not:
from keras.models import Model
from detector import Detector
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
model_path = 'incepv3_transfer.h5'
detective = Detector(model_path)
bird_img = 'b1.jpeg'
classes = detective.detect(bird_img)
print(classes)
bird_img = 'dog1.jpg'
classes = detective.detect(bird_img)
print(classes)
the output is always:
[[1.]]