Я тренирую модель классификации для классификации клеток, и моя модель основана на этой статье: https://www.nature.com/articles/s41598-019-50010-9. Поскольку мой набор данных состоит всего из 10 изображений, я выполнил увеличение изображения, чтобы искусственно увеличить размер набора данных до 3000 изображений, которые затем были разделены на 2400 обучающих изображений и 600 проверочных изображений.
Однако в то время как потери при обучении и точность улучшались при большем количестве итераций, потери при проверке быстро увеличивались, в то время как точность проверки оставалась неизменной на уровне 0,0000e+00.
Сильно ли переоснащает мою модель с самого начала?
Код, который я использовал, показан ниже:
import keras
import tensorflow as tf
from tensorflow.keras import backend as K
from tensorflow.keras.models import Model, load_model, Sequential, model_from_json, load_model
from tensorflow.keras.layers import Input, BatchNormalization, Activation, Flatten, Dense, LeakyReLU
from tensorflow.python.keras.layers.core import Lambda, Dropout
from tensorflow.python.keras.layers.convolutional import Conv2D, Conv2DTranspose, UpSampling2D
from tensorflow.python.keras.layers.pooling import MaxPooling2D, AveragePooling2D
from tensorflow.python.keras.layers.merge import Concatenate, Add
from tensorflow.keras import backend as K
from tensorflow.keras.callbacks import ModelCheckpoint, LearningRateScheduler, ReduceLROnPlateau, EarlyStopping
from tensorflow.keras.optimizers import *
img_channel = 1
input_size = (512, 512, 1)
inputs = Input(shape = input_size)
initial_input = Lambda(lambda x: x) (inputs) #Ensure input value is between 0 and 1 to avoid negative loss
kernel_size = (3,3)
pad = 'same'
model = Sequential()
filters = 2
c1 = Conv2D(filters, kernel_size, padding = pad, kernel_initializer = 'he_normal')(initial_input)
b1 = BatchNormalization()(c1)
a1 = Activation('elu')(b1)
p1 = AveragePooling2D()(a1)
c2 = Conv2D(filters, kernel_size, padding = pad, kernel_initializer = 'he_normal')(p1)
b2 = BatchNormalization()(c2)
a2 = Activation('elu')(b2)
p2 = AveragePooling2D()(a2)
c3 = Conv2D(filters, kernel_size, padding = pad, kernel_initializer = 'he_normal')(p2)
b3 = BatchNormalization()(c3)
a3 = Activation('elu')(b3)
p3 = AveragePooling2D()(a3)
c4 = Conv2D(filters, kernel_size, padding = pad, kernel_initializer = 'he_normal')(p3)
b4 = BatchNormalization()(c4)
a4 = Activation('elu')(b4)
p4 = AveragePooling2D()(a4)
c5 = Conv2D(filters, kernel_size, padding = pad, kernel_initializer = 'he_normal')(p4)
b5 = BatchNormalization()(c5)
a5 = Activation('elu')(b5)
p5 = AveragePooling2D()(a5)
f = Flatten()(p5)
d1 = Dense(128, activation = 'elu')(f)
d2 = Dense(no_of_img, activation = 'softmax')(d1)
model = Model(inputs = [inputs], outputs = [d2])
print(model.summary())
learning_rate = 0.001
decay_rate = 0.0001
model.compile(optimizer = SGD(lr = learning_rate, decay = decay_rate, momentum = 0.9, nesterov = False),
loss = 'categorical_crossentropy', metrics = ['accuracy'])
perf_lr_scheduler = ReduceLROnPlateau(monitor = 'val_loss', factor = 0.9, patience = 3,
verbose = 1, min_delta = 0.01, min_lr = 0.000001)
model_earlystop = EarlyStopping(monitor = 'val_loss', min_delta = 0.001, patience = 10, restore_best_weights = True)
#Convert labels to binary matrics
img_aug_label = to_categorical(img_aug_label, num_classes = no_of_img)
#Convert images to float to between 0 and 1
img_aug = np.float32(img_aug)/255
plt.imshow(img_aug[0,:,:,0])
plt.show()
#Train on augmented images
model.fit(
img_aug,
img_aug_label,
batch_size = 4,
epochs = 100,
validation_split = 0.2,
shuffle = True,
callbacks = [perf_lr_scheduler],
verbose = 2)
Вывод моей модели показан ниже:
Train on 2400 samples, validate on 600 samples
Epoch 1/100
2400/2400 - 12s - loss: 0.6474 - accuracy: 0.8071 - val_loss: 9.8161 - val_accuracy: 0.0000e+00
Epoch 2/100
2400/2400 - 10s - loss: 0.0306 - accuracy: 0.9921 - val_loss: 10.1733 - val_accuracy: 0.0000e+00
Epoch 3/100
2400/2400 - 10s - loss: 0.0058 - accuracy: 0.9996 - val_loss: 10.9820 - val_accuracy: 0.0000e+00
Epoch 4/100
Epoch 00004: ReduceLROnPlateau reducing learning rate to 0.0009000000427477062.
2400/2400 - 10s - loss: 0.0019 - accuracy: 1.0000 - val_loss: 11.3029 - val_accuracy: 0.0000e+00
Epoch 5/100
2400/2400 - 10s - loss: 0.0042 - accuracy: 0.9992 - val_loss: 11.9037 - val_accuracy: 0.0000e+00
Epoch 6/100
2400/2400 - 10s - loss: 0.0024 - accuracy: 0.9996 - val_loss: 11.5218 - val_accuracy: 0.0000e+00
Epoch 7/100
Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.0008100000384729356.
2400/2400 - 10s - loss: 9.9053e-04 - accuracy: 1.0000 - val_loss: 11.7658 - val_accuracy: 0.0000e+00
Epoch 8/100
2400/2400 - 10s - loss: 0.0011 - accuracy: 1.0000 - val_loss: 12.0437 - val_accuracy: 0.0000e+00
Epoch 9/100
d2 = Dense(no_of_img, activation = 'softmax')(d1)
наd2 = Dense(no_of_img)(d1)
и посмотреть, есть ли какие-либо изменения в результатах? - person Vishnuvardhan Janapati   schedule 25.04.2020