我正在训练TACO数据集上的unet模型，我的输出出现问题。我的验证损失比我的训练损失低很多，而且我不确定这是否是一件好事。 由于TACO数据集是包含1500张图像的COCO格式数据集，因此我通过让train_generator包含图像0-1199和val_generator包含图像1200-1499来拆分数据。然后，我使用以下功能扩充数据：
def augmentationsGenerator(gen, augGeneratorArgs, seed=None):
# Initialize the image data generator with args provided
image_gen = ImageDataGenerator(**augGeneratorArgs)
# Remove the brightness argument for the mask. Spatial arguments similar to image.
augGeneratorArgs_mask = augGeneratorArgs.copy()
_ = augGeneratorArgs_mask.pop('brightness_range', None)
# Initialize the mask data generator with modified args
mask_gen = ImageDataGenerator(**augGeneratorArgs_mask)
np.random.seed(seed if seed is not None else np.random.choice(range(9999)))
for img, mask in gen:
seed = np.random.choice(range(9999))
# keep the seeds syncronized otherwise the augmentation of the images
# will end up different from the augmentation of the masks
g_x = image_gen.flow(255*img,
batch_size = img.shape[0],
seed = seed,
shuffle=True)
g_y = mask_gen.flow(mask,
batch_size = mask.shape[0],
seed = seed,
shuffle=True)
img_aug = next(g_x)/255.0
mask_aug = next(g_y)
yield img_aug, mask_aug
具有以下参数：
augGeneratorArgs = dict(featurewise_center = False,
samplewise_center = False,
rotation_range = 5,
width_shift_range = 0.01,
height_shift_range = 0.01,
brightness_range = (0.8,1.2),
shear_range = 0.01,
zoom_range = [1, 1.25],
horizontal_flip = True,
vertical_flip = False,
fill_mode = 'reflect',
data_format = 'channels_last')
我的模型代码是：
IMG_WIDTH = 224
IMG_HEIGHT = 224
IMG_CHANNELS = 3
epochs = 25
validation_steps = val_size
steps_per_epoch = train_size
x = 32
##Creating the model
initializer = "he_normal"
###Building U-Net Model
##Input Layer
inputs = Input((IMG_WIDTH, IMG_HEIGHT, IMG_CHANNELS))
##Converting inputs to float
s = tf.keras.layers.Lambda(lambda x: x / 255)(inputs)
##Contraction
c1 = tf.keras.layers.Conv2D(x, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(s)
c1 = tf.keras.layers.Dropout(0.1)(c1)
c1 = tf.keras.layers.Conv2D(x, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c1)
p1 = tf.keras.layers.MaxPooling2D((2,2))(c1)
c2 = tf.keras.layers.Conv2D(x*2, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(p1)
c2 = tf.keras.layers.Dropout(0.1)(c2)
c2 = tf.keras.layers.Conv2D(x*2, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c2)
p2 = tf.keras.layers.MaxPooling2D((2,2))(c2)
c3 = tf.keras.layers.Conv2D(x*4, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(p2)
c3 = tf.keras.layers.Dropout(0.2)(c3)
c3 = tf.keras.layers.Conv2D(x*4, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c3)
p3 = tf.keras.layers.MaxPooling2D((2,2))(c3)
c4 = tf.keras.layers.Conv2D(x*8, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(p3)
c4 = tf.keras.layers.Dropout(0.2)(c4)
c4 = tf.keras.layers.Conv2D(x*8, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c4)
p4 = tf.keras.layers.MaxPooling2D((2,2))(c4)
c5 = tf.keras.layers.Conv2D(x*16, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(p4)
c5 = tf.keras.layers.Dropout(0.3)(c5)
c5 = tf.keras.layers.Conv2D(x*16, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c5)
##Expansion
u6 = tf.keras.layers.Conv2DTranspose(x*8, (2,2), strides=(2,2), padding="same")(c5)
u6 = tf.keras.layers.concatenate([u6, c4])
c6 = tf.keras.layers.Conv2D(x*8, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(u6)
c6 = tf.keras.layers.Dropout(0.2)(c6)
c6 = tf.keras.layers.Conv2D(x*8, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c6)
u7 = tf.keras.layers.Conv2DTranspose(x*4, (2,2), strides=(2,2), padding="same")(c6)
u7 = tf.keras.layers.concatenate([u7, c3])
c7 = tf.keras.layers.Conv2D(x*4, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(u7)
c7 = tf.keras.layers.Dropout(0.2)(c7)
c7 = tf.keras.layers.Conv2D(x*4, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c7)
u8 = tf.keras.layers.Conv2DTranspose(x*2, (2,2), strides=(2,2), padding="same")(c7)
u8 = tf.keras.layers.concatenate([u8, c2])
c8 = tf.keras.layers.Conv2D(x*2, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(u8)
c8 = tf.keras.layers.Dropout(0.1)(c8)
c8 = tf.keras.layers.Conv2D(x*2, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c8)
u9 = tf.keras.layers.Conv2DTranspose(x, (2,2), strides=(2,2), padding="same")(c8)
u9 = tf.keras.layers.concatenate([u9, c1], axis=3)
c9 = tf.keras.layers.Conv2D(x, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(u9)
c9 = tf.keras.layers.Dropout(0.1)(c9)
c9 = tf.keras.layers.Conv2D(x, (3,3), activation="relu", kernel_initializer=initializer, padding="same")(c9)
##Output Layer
outputs = tf.keras.layers.Conv2D(61, (1,1), activation="softmax")(c9)
##Defining Model
model = tf.keras.Model(inputs=[inputs], outputs=[outputs])
##Compiling Model
model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])
##Defining callbacks
callbacks = [
tf.keras.callbacks.ModelCheckpoint('/content/drive/My Drive/THESIS/taco_2-2_final_retry.h5', verbose=1, save_best_only=True),
tf.keras.callbacks.EarlyStopping(patience=6, monitor="val_loss"),
tf.keras.callbacks.TensorBoard(log_dir=logs),
tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience = 2, min_lr = 0.001)]
##Training the model
results = model.fit(x = train_gen_aug,
validation_data = val_gen_aug,
steps_per_epoch = steps_per_epoch,
validation_steps = validation_steps,
epochs = epochs,
callbacks=callbacks,
verbose = True)
前几个时期产生以下结果：
Epoch 1/25
1200/1200 [==============================] - ETA: 0s - loss: 0.8035 - sparse_categorical_accuracy: 0.9495
Epoch 00001: val_loss improved from inf to 0.22116, saving model to /content/drive/My Drive/THESIS/taco_2-2_final_retry.h5
1200/1200 [==============================] - 7408s 6s/step - loss: 0.8035 - sparse_categorical_accuracy: 0.9495 - val_loss: 0.2212 - val_sparse_categorical_accuracy: 0.9859 - lr: 0.0010
Epoch 2/25
1200/1200 [==============================] - ETA: 0s - loss: 0.7942 - sparse_categorical_accuracy: 0.9501
Epoch 00002: val_loss improved from 0.22116 to 0.21732, saving model to /content/drive/My Drive/THESIS/taco_2-2_final_retry.h5
1200/1200 [==============================] - 6378s 5s/step - loss: 0.7942 - sparse_categorical_accuracy: 0.9501 - val_loss: 0.2173 - val_sparse_categorical_accuracy: 0.9861 - lr: 0.0010
所以我的问题是，验证损失是否比我的训练损失还低/可以接受？以及如何进一步减少验证损失？我的目标是约0.0倍。是否添加更多的辍学层或增加辍学值？减少/增加每层神经元的数量？
答案 0 :(得分：2)
几乎总是训练损失都低于验证损失，所以还可以。
关于减少Val损失，您必须解决各种问题。 如：
1）更改augGeneratorArgs超参数
2）每层添加更多的层或神经元
3）添加更多辍学对象以减少过度拟合。
4）增加/减少时期
5）绘制可视化的火车/ Val损失图，以检查模型是否过拟合。