如何在转学Resnet50中提高我的验证准确性？

Question

我正在训练一个模型，并使用Resnet50权重，在更多的时期内，我的火车精度会提高，但验证精度会低于火车精度，并且不会提高。 是什么原因？ 下面是我的转学代码

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline 
import cv2
import os
print(os.listdir("/kaggle/input/contaguis-skin-diease-dataset/Contaguis_Skin_Diease_dataset/Train"))

NUM_CLASSES = 5

CHANNELS = 3

IMAGE_RESIZE = 224
RESNET50_POOLING_AVERAGE = 'avg'
DENSE_LAYER_ACTIVATION = 'softmax'
OBJECTIVE_FUNCTION = 'categorical_crossentropy'

LOSS_METRICS = ['accuracy']

NUM_EPOCHS = 20
EARLY_STOP_PATIENCE = 3

STEPS_PER_EPOCH_TRAINING = 10
STEPS_PER_EPOCH_VALIDATION = 10

BATCH_SIZE_TRAINING = 100
BATCH_SIZE_VALIDATION = 100
BATCH_SIZE_TESTING = 1

使用tensorflow.keras

import tensorflow as tf
from tensorflow.keras.applications import ResNet50
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

resNet 50

resnet_weights_path = '/kaggle/input/resnet50/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'

model = Sequential()

model.add(ResNet50(include_top = False, pooling = RESNET50_POOLING_AVERAGE, weights = resnet_weights_path))
model.add(Dense(512,activation='relu')) #
model.add(Dense(NUM_CLASSES, activation = DENSE_LAYER_ACTIVATION))

model.layers[0].trainable = False

优化器

from tensorflow.keras import optimizers
sgd = optimizers.SGD(lr = 0.01, decay = 1e-6, momentum = 0.9, nesterov = True)
model.compile(optimizer = sgd, loss = OBJECTIVE_FUNCTION, metrics = LOSS_METRICS)

from keras.applications.resnet50 import preprocess_input
from keras.preprocessing.image import ImageDataGenerator

image_size = IMAGE_RESIZE

# preprocessing_function is applied on each image but only after re-sizing & augmentation (resize => augment => pre-process)
data_generator = ImageDataGenerator(preprocessing_function=preprocess_input)

# flow_From_directory generates batches of augmented data (where augmentation can be color conversion, etc)
train_generator = data_generator.flow_from_directory(
        '/kaggle/input/contaguis-skin-diease-dataset/Contaguis_Skin_Diease_dataset/Train',
        target_size=(image_size, image_size),
        batch_size=BATCH_SIZE_TRAINING,
        class_mode='categorical')

validation_generator = data_generator.flow_from_directory(
        '/kaggle/input/contaguis-skin-diease-dataset/Contaguis_Skin_Diease_dataset/Valid',
        target_size=(image_size, image_size),
        batch_size=BATCH_SIZE_VALIDATION,
        class_mode='categorical') 

使用回调防止模型过拟合

from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint

cb_early_stopper = EarlyStopping(monitor = 'val_loss', patience = EARLY_STOP_PATIENCE)
cb_checkpointer = ModelCheckpoint(filepath = '../working/best.hdf5', monitor = 'val_loss', save_best_only = True, mode = 'auto')

以20个时期训练我的模型

fit_history = model.fit_generator(
        train_generator,
        steps_per_epoch=STEPS_PER_EPOCH_TRAINING,
        epochs = NUM_EPOCHS,
        validation_data=validation_generator,
        validation_steps=STEPS_PER_EPOCH_VALIDATION,
        callbacks=[cb_checkpointer, cb_early_stopper]
)
model.load_weights("../working/best.hdf5")

enter image description here

enter image description here