我的任务是根据缺陷对种子进行分类。我在 7 个班级中有大约 14k 张图片（它们的大小不相等，有些班级的照片更多，有些班级的照片更少）。我尝试从头开始训练 Inception V3，我的准确率约为 90%。然后我尝试使用带有 ImageNet 权重的预训练模型进行迁移学习。我inception_v3从applications没有顶部 fc 层的情况下导入，然后在文档中添加了我自己的。我以以下代码结束：
# Setting dimensions
img_width = 454
img_height = 227
###########################
# PART 1 - Creating Model #
###########################
# Creating InceptionV3 model without Fully-Connected layers
base_model = InceptionV3(weights='imagenet', include_top=False, input_shape = (img_height, img_width, 3))
# Adding layers which will be fine-tunned
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(7, activation='softmax')(x)
# Creating final model
model = Model(inputs=base_model.input, outputs=predictions)
# Plotting model
plot_model(model, to_file='inceptionV3.png')
# Freezing Convolutional layers
for layer in base_model.layers:
layer.trainable = False
# Summarizing layers
print(model.summary())
# Compiling the CNN
model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])
##############################################
# PART 2 - Images Preproccessing and Fitting #
##############################################
# Fitting the CNN to the images
train_datagen = ImageDataGenerator(rescale = 1./255,
rotation_range=30,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True,
preprocessing_function=preprocess_input,)
valid_datagen = ImageDataGenerator(rescale = 1./255,
preprocessing_function=preprocess_input,)
train_generator = train_datagen.flow_from_directory("dataset/training_set",
target_size=(img_height, img_width),
batch_size = 4,
class_mode = "categorical",
shuffle = True,
seed = 42)
valid_generator = valid_datagen.flow_from_directory("dataset/validation_set",
target_size=(img_height, img_width),
batch_size = 4,
class_mode = "categorical",
shuffle = True,
seed = 42)
STEP_SIZE_TRAIN = train_generator.n//train_generator.batch_size
STEP_SIZE_VALID = valid_generator.n//valid_generator.batch_size
# Save the model according to the conditions
checkpoint = ModelCheckpoint("inception_v3_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_acc', min_delta=0, patience=10, verbose=1, mode='auto')
#Training the model
history = model.fit_generator(generator=train_generator,
steps_per_epoch=STEP_SIZE_TRAIN,
validation_data=valid_generator,
validation_steps=STEP_SIZE_VALID,
epochs=25,
callbacks = [checkpoint, early])
但我得到了糟糕的结果：45% 的准确率。我认为它应该更好。我有一些假设可能会出错：
- 我从头开始对缩放图像（299x299）和非缩放图像（227x454）进行了训练，但它失败了（或者我的尺寸顺序失败了）。
- 在我使用迁移学习
preprocessing_function=preprocess_input时（在网上发现它非常重要的文章，所以我决定添加它）。 - 添加
rotation_range=30、width_shift_range=0.2、height_shift_range=0.2和horizontal_flip = Truewhile 迁移学习以进一步增强数据。 - 也许亚当优化器是个坏主意？例如，我应该尝试 RMSprop 吗？
- 我也应该用小学习率的 SGD 微调一些 conv 层吗？
还是我失败了其他事情？
编辑：我发布了一段训练历史。也许它包含有价值的信息：
EDIT2：随着 InceptionV3 参数的改变：
VGG16进行比较：
