def train(batch, epochs, num_classes, size, weights, tclasses, tflite):
"""Train the model.
# Arguments
batch: Integer, The number of train samples per batch.
epochs: Integer, The number of train iterations.
num_classes, Integer, The number of classes of dataset.
size: Integer, image size.
weights, String, The pre_trained model weights.
tclasses, Integer, The number of classes of pre-trained model.
tflite, Boolean, Convert the final model to a tflite model
"""
train_generator, validation_generator, count1, count2 = generate(
batch, size)
if weights:
if tclasses:
print("fine tunning")
model = MobileNetv2((size, size, 3), tclasses)
model = fine_tune(num_classes, weights, model)
else:
print("Loading Weights")
model = MobileNetv2((size, size, 3), num_classes)
model = keep_training(weights, model)
else:
model = MobileNetv2((size, size, 3), num_classes)
opt = Adam()
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
hist = model.fit_generator(train_generator,
validation_data=validation_generator,
steps_per_epoch=count1 // batch,
validation_steps=count2 // batch,
epochs=epochs,
callbacks=create_callbacks())
generate_report(model, validation_generator, batch, count2)
if not os.path.exists('model'):
os.makedirs('model')
df = pd.DataFrame.from_dict(hist.history)
df.to_csv('model/hist.csv', encoding='utf-8', index=False)
print("Saving weights")
model.save_weights('model/weights.h5')
model_name = "mobile_model.h5"
if tflite:
print("Saving model")
model.save(model_name)
print("Converting model")
convert_to_lite(model_name)
def train(batch, epochs, num_classes, size, weights, tclasses,train_path,valid_path):
"""Train the model.
# Arguments
batch: Integer, The number of train samples per batch.
epochs: Integer, The number of train iterations.
num_classes, Integer, The number of classes of dataset.
size: Integer, image size.
weights, String, The pre_trained model weights.
tclasses, Integer, The number of classes of pre-trained model.
"""
train_generator, validation_generator, count1, count2 = generate(batch, size,train_path,valid_path)
if weights:
model = MobileNetv2((size, size, 3), tclasses)
model = fine_tune(num_classes, weights, model)
else:
model = MobileNetv2((size, size, 3), num_classes)
opt = Adam()
earlystop = EarlyStopping(monitor='val_acc', patience=30, verbose=0, mode='auto')
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
hist = model.fit_generator(
train_generator,
validation_data=validation_generator,
steps_per_epoch=count1 // batch,
validation_steps=count2 // batch,
epochs=epochs,
callbacks=[earlystop])
# rootDir='/home/eric/data/scene'
# for i in range(10):
# test_path='group'+str(i)+'_test.txt'
# testfilepath=os.path.join(rootDir,test_path)
# testDf=pd.read_csv(testfilepath,header=None) #加载papa.txt,指定它的分隔符是 \t
# testDf.rename(columns={0:"filename",1:'class'},inplace=True)
# datagen3 = ImageDataGenerator(rescale=1. / 255)
# validation_generator = datagen3.flow_from_dataframe(
# dataframe=testDf,
# directory=rootDir,
# x_col="filename",
# y_col="class",
# subset="training",
# # classes=labels,
# target_size=[size, size],
# batch_size=batch,
# class_mode='categorical')
# result=model.evaluate_generator(validation_generator,steps=testDf.shape[0]//batch)
# print(result)
if not os.path.exists('model'):
os.makedirs('model')
df = pd.DataFrame.from_dict(hist.history)
df.to_csv('model/hist.csv', encoding='utf-8', index=False)
model.save_weights('model/weights_'+train_path.split('.')[0]+'.h5')
def train(batch, epochs, num_classes, size, weights, tclasses):
"""Train the model.
# Arguments
batch: Integer, The number of train samples per batch.
epochs: Integer, The number of train iterations.
num_classes, Integer, The number of classes of dataset.
size: Integer, image size.
weights, String, The pre_trained model weights.
tclasses, Integer, The number of classes of pre-trained model.
"""
# For the CuDnn compatible
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.log_device_placement = True
sess = tf.Session(config=config)
set_session(sess)
train_generator, validation_generator, count1, count2 = generate(
batch, size)
if weights:
model = MobileNetv2((size, size, 3), tclasses)
model = fine_tune(num_classes, weights, model)
else:
model = MobileNetv2((size, size, 3), num_classes)
opt = Adam()
earlystop = EarlyStopping(monitor='val_acc',
patience=30,
verbose=0,
mode='auto')
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
hist = model.fit_generator(train_generator,
validation_data=validation_generator,
steps_per_epoch=count1 // batch,
validation_steps=count2 // batch,
epochs=epochs,
callbacks=[earlystop])
if not os.path.exists('model'):
os.makedirs('model')
df = pd.DataFrame.from_dict(hist.history)
df.to_csv('model/hist.csv', encoding='utf-8', index=False)
model.save_weights('model/weights.h5')
def train(batch, epochs, num_classes, size, weights, tclasses):
"""Train the model.
# Arguments
batch: Integer, The number of train samples per batch.
epochs: Integer, The number of train iterations.
num_classes, Integer, The number of classes of dataset.
size: Integer, image size.
weights, String, The pre_trained model weights.
tclasses, Integer, The number of classes of pre-trained model.
"""
train_generator, validation_generator, count1, count2 = generate(batch, size)
if weights:
model = MobileNetv2((size, size, 3), tclasses)
model = fine_tune(num_classes, weights, model)
else:
model = MobileNetv2((size, size, 3), num_classes)
opt = Adam()
earlystop = EarlyStopping(monitor='val_acc', patience=30, verbose=0, mode='auto')
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
class Save(keras.callbacks.Callback):
def __init__(self):
self.max_acc = 0.0
def on_epoch_begin(self, epoch, logs=None):
pass
def on_epoch_end(self, epoch, logs=None):
self.val_acc = logs["val_acc"]
if epoch != 0:
#if self.val_acc > self.max_acc and self.val_acc > 0.8:
if self.val_acc > self.max_acc:
model.save("./log/model/kears_model_"+str(epoch)+ "_acc="+str(self.val_acc)+".h5")
self.max_acc = self.val_acc
save_function = Save()
hist = model.fit_generator(
train_generator,
validation_data=train_generator,
steps_per_epoch=count1 // batch,
validation_steps=count2 // batch,
epochs=epochs,
callbacks=[TensorBoard(log_dir='./log'),save_function,earlystop])
#df = pd.DataFrame.from_dict(hist.history)
#df.to_csv('model/hist.csv', encoding='utf-8', index=False)
model.save_weights('log/model/weights.h5')
def train(batch, epochs, num_classes, size, weights, tclasses):
"""Train the model.
# Arguments
batch: Integer, The number of train samples per batch.
epochs: Integer, The number of train iterations.
num_classes, Integer, The number of classes of dataset.
size: Integer, image size.
weights, String, The pre_trained model weights.
tclasses, Integer, The number of classes of pre-trained model.
"""
train_generator, validation_generator, count1, count2 = generate(
batch, size)
if weights:
model = MobileNetv2((size, size, 3), tclasses)
model = fine_tune(num_classes, weights, model)
else:
model = MobileNetv2((size, size, 3), num_classes, mode=args.mode)
print(model.summary())
model = multi_gpu_model(model, gpus=gpu_count)
opt = Adam()
earlystop = EarlyStopping(monitor='val_acc',
patience=30,
verbose=0,
mode='auto')
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
hist = model.fit_generator(train_generator,
validation_data=validation_generator,
steps_per_epoch=count1 // batch,
validation_steps=count2 // batch,
epochs=epochs,
callbacks=[earlystop])
if not os.path.exists('model'):
os.makedirs('model')
df = pd.DataFrame.from_dict(hist.history)
df.to_csv('model/hist.csv', encoding='utf-8', index=False)
model.save_weights(args.save_model)
def train(batch, epochs, num_classes, size, weights, tclasses):
"""Train the model.
# Arguments
batch: Integer, The number of train samples per batch.
epochs: Integer, The number of train iterations.
num_classes, Integer, The number of classes of dataset.
size: Integer, image size.
weights, String, The pre_trained model weights.
tclasses, Integer, The number of classes of pre-trained model.
"""
train_data, validation_data, test_data = get_mnist_dataset()
if weights:
model = MobileNetv2((size, size, 1), tclasses)
model = fine_tune(num_classes, weights, model)
else:
model = MobileNetv2((size, size, 1), num_classes)
opt = RMSprop()
earlystop = EarlyStopping(monitor='val_acc',
patience=10,
verbose=1,
mode='auto')
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
history = model.fit(train_data[0],
train_data[1],
validation_data=validation_data,
batch_size=500,
epochs=epochs,
shuffle=True,
callbacks=[earlystop])
if not os.path.exists('model'):
os.makedirs('model')
df = pd.DataFrame.from_dict(history.history)
df.to_csv('model/history.csv', encoding='utf-8', index=False)
model.save_weights('model/weights.h5')
predictions = model.predict(test_data, verbose=1)
return history
def model_feed(size, num_classes):
'''
Wrapper the model creation
#Arguments
num_classes: Integer, The number of classes to create a model.
size: tuple, The shape of the data.
#Return:
The model
'''
return MobileNetv2(size, num_classes)
def train_factory(MODEL_NAME):
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
config.gpu_options.allow_growth = True
set_session(tf.Session(config=config))
# model = CCR(input_shape=(img_width,img_height,1),classes=charset_size)
# model = LeNet.build(width=img_width, height=img_height, depth=1, classes=charset_size)
# model = ResNet.build_model(SHAPE=(img_width,img_height,1), classes=charset_size)
# vgg net 5
# MODEL_PATH='trained_model/vggnet5.hdf5'
# model=VGGNet5.vgg(input_shape=(img_width,img_height,1),classes=charset_size)
model=None
if(MODEL_NAME=='inception_resnet_v2'):
model=InceptionResNetV2.inception_resnet_v2(input_shape=(img_width,img_height,3),classes=charset_size,weights='./trained_model/inception_resnet_v2/inception_resnet_v2.12-0.8244.hdf5')
elif(MODEL_NAME=='xception'):
# xeception
model=Xception.Xception((img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='mobilenet_v2'):
#mobilenet v2
model=MobileNetv2.MobileNet_v2((img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='inception_v3'):
#mobilenet v2
model=Inception_v3.inception((img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='vgg16'):
model=VGGNet.vgg(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='vgg19'):
model=VGG19.VGG19(input_shape=(img_width,img_height,3),classes=charset_size,weights='weights/vgg19_weights_tf_dim_ordering_tf_kernels.h5')
elif(MODEL_NAME=='resnet50'):
model=ResNet50.resnet(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='inception_v4'):
model=inception_v4.inception_v4(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='resnet34'):
model=ResNet34.ResNet34(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='densenet121'):
model=DenseNet.DenseNet(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='densenet161'):
model=DenseNet.DenseNet(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='shufflenet_v2'):
model=ShuffleNetV2.ShuffleNetV2(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='resnet_attention_56'):
model=Resnet_Attention_56.Resnet_Attention_56(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='squeezenet'):
model=SqueezeNet.SqueezeNet(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='seresnet50'):
model=SEResNet50.SEResNet50(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='se_resnext'):
model=SEResNext.SEResNext(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='nasnet'):
model=NASNet.NASNetLarge(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='custom'):
model=Custom_Network.Custom_Network(input_shape=(img_width,img_height,3),classes=charset_size)
elif(MODEL_NAME=='resnet18'):
model=ResnetBuilder.build_resnet_18(input_shape=(img_width,img_height,3),num_outputs=charset_size)
print(model.summary())
train(model,MODEL_NAME)
def train(batch, epochs, num_classes, size, weights, tclasses):
"""Train the model.
# Arguments
batch: Integer, The number of train samples per batch.
epochs: Integer, The number of train iterations.
num_classes, Integer, The number of classes of dataset.
size: Integer, image size.
weights, String, The pre_trained model weights.
tclasses, Integer, The number of classes of pre-trained model.
"""
train_generator, validation_generator, count1, count2 = generate(batch, size)
train_generator = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
rotation_range=90,
width_shift_range=0.2,
height_shift_range=0.2,
brightness_range=(1, 1.3),
horizontal_flip=True)
directory="/home/gnss/Desktop/garbage_train"
train_generator = MixupImageDataGenerator(generator=train_generator,
directory=directory,
batch_size=32,
img_height=224,
img_width=224,
subset='training')
if weights:
model = MobileNetv2((size, size, 3), tclasses)
model = fine_tune(num_classes, weights, model)
print(num_classes)
else:
model = MobileNetv2((size, size, 3), num_classes)
print(num_classes)
opt = Adam(1e-2)
# earlystop = EarlyStopping(monitor='val_acc', patience=30, verbose=0, mode='auto')
tensorboard = TensorBoard('/home/gnss/Desktop/MobileNetV2/logs',write_images=True)
# reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5,patience=3, verbose=0, mode='auto', epsilon=0.0001, cooldown=0, min_lr=0)
warmup_epoch = 5
warm_up_lr = WarmUpCosineDecayScheduler(learning_rate_base=1e-2,
total_steps=count1 // batch)
checkpointer = ModelCheckpoint(filepath='/home/gnss/Desktop/MobileNetV2/mobilenet.h5',verbose=1,save_best_only=True)
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
# lr=XTensorBoard('/home/gnss/Desktop/MobileNetV2/logslr')
hist = model.fit_generator(
train_generator,
validation_data=validation_generator,
steps_per_epoch=count1 // batch,
validation_steps=count2 // batch,
epochs=epochs,
callbacks=[warm_up_lr,tensorboard,checkpointer])
'''
learning_rate_base=1e-2
total_steps=count1 // batch
plt.plot(warm_up_lr.learning_rates)
plt.xlabel('Step', fontsize=20)
plt.ylabel('lr', fontsize=20)
plt.axis([0, total_steps, 0, learning_rate_base*1.1])
plt.xticks(np.arange(0, total_steps, 50))
plt.grid()
plt.title('Cosine decay with warmup', fontsize=20)
plt.show()
'''
if not os.path.exists('model'):
os.makedirs('model')
df = pd.DataFrame.from_dict(hist.history)
df.to_csv('model/hist.csv', encoding='utf-8', index=False)
model.save_weights('model/weights.h5')
from keras.preprocessing import image
import numpy as np
from keras.models import Model, load_model
from mobilenet_v2 import MobileNetv2
model = MobileNetv2((224,224, 3), 34)
model.load_weights("./model/weights.h5")
img_path = '/home/eric/data/flower_photos/roses/353897245_5453f35a8e.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
# x = preprocess_input(x)
x=x/255.0
print(x[0])
preds = model.predict(x)
print(preds)
# preds=np.argmax(preds)
# # print('Predicted:', decode_predictions(preds))
# print(preds)
# print(label_dict[str(preds)])