解释损失和度量曲线

Question

我正在尝试使用以下参数来训练UNET模型：

droput_: 0.2,
activation_: sigmoid,
activation_inner_: relu,
learning_rate_: 0.0001,
epsilon_: 1e-07,
loss : mse,
metric : rmse,
kernel_regularizer=regularizers.l1_l2(l1=0.01, l2=0.01), bias_regularizer=regularizers.l1_l2(l1=0.01, l2=0.01)

我运行了模型，并获得了以下损失和度量图。

蓝色=训练， 橙色=验证

，请帮助解释损失（MSE）和公制（RMSE）图。

• 太合适了吗？
• 公制图还可以吗？

Answer 1

当损失减少而对均方错误或更长的时间造成切碎的影响时，数据就足够独特了，或者它继续执行样本的行为。

[样本]：

import os
from os.path import exists

import tensorflow as tf
import h5py

from tensorflow_examples.models.pix2pix import pix2pix
import matplotlib.pyplot as plt

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Variables
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
OUTPUT_CLASSES = 3

database_buffer = "F:\\models\\buffer\\" + os.path.basename(__file__).split('.')[0] + "\\TF_DataSets_01.h5"
database_buffer_dir = os.path.dirname(database_buffer)

checkpoint_path = "F:\\models\\checkpoint\\" + os.path.basename(__file__).split('.')[0] + "\\TF_DataSets_01.h5"
checkpoint_dir = os.path.dirname(checkpoint_path)
loggings = "F:\\models\\checkpoint\\" + os.path.basename(__file__).split('.')[0] + "\\loggings.log"

if not exists(checkpoint_dir) : 
    os.mkdir(checkpoint_dir)
    print("Create directory: " + checkpoint_dir)
    
if not exists(database_buffer_dir) : 
    os.mkdir(database_buffer_dir)
    print("Create directory: " + database_buffer_dir)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Functions
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
def unet_model(output_channels:int):
    inputs = tf.keras.layers.Input(shape=[32, 32, 3])
    # inputs = tf.keras.layers.Input(shape=[128, 128, 3])

    # Downsampling through the model
    skips = down_stack(inputs)
    x = skips[-1]
    skips = reversed(skips[:-1])

    # Upsampling and establishing the skip connections
    for up, skip in zip(up_stack, skips):
        x = up(x)
        concat = tf.keras.layers.Concatenate()
        x = concat([x, skip])

    # This is the last layer of the model
    last = tf.keras.layers.Conv2DTranspose(
    filters=output_channels, kernel_size=3, strides=2,
    padding='same')  #64x64 -> 128x128

    x = last(x)

    return tf.keras.Model(inputs=inputs, outputs=x, name="U-net")

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
DataSet
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()

train_generator = tf.keras.preprocessing.image.ImageDataGenerator(
    featurewise_center=True,
    featurewise_std_normalization=True,
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    horizontal_flip=True,
    validation_split=0.2)
    
train_generator.fit(x_train)


"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Initialize
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
# base_model = tf.keras.applications.MobileNetV2(input_shape=[128, 128, 3], include_top=False)
base_model = tf.keras.applications.MobileNetV2(input_shape=[32, 32, 3], include_top=False)

# Use the activations of these layers
layer_names = [
    'block_1_expand_relu',   # 64x64
    'block_3_expand_relu',   # 32x32
    'block_6_expand_relu',   # 16x16
    'block_13_expand_relu',  # 8x8
    'block_16_project',      # 4x4
]
base_model_outputs = [base_model.get_layer(name).output for name in layer_names]

# Create the feature extraction model
down_stack = tf.keras.Model(inputs=base_model.input, outputs=base_model_outputs)
down_stack.trainable = False

up_stack = [
    pix2pix.upsample(512, 3),  # 4x4 -> 8x8
    pix2pix.upsample(256, 3),  # 8x8 -> 16x16
    pix2pix.upsample(128, 3),  # 16x16 -> 32x32
    pix2pix.upsample(64, 3),   # 32x32 -> 64x64
]

unet_model = unet_model( output_channels=OUTPUT_CLASSES )
unet_model.summary()

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Optimizer
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
optimizer = tf.keras.optimizers.Nadam( learning_rate=0.0001, beta_1=0.9, beta_2=0.999, epsilon=1e-07, name='Nadam' )

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Loss Fn
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""                               
lossfn = tf.keras.losses.MeanSquaredError( reduction=tf.keras.losses.Reduction.AUTO, name='mean_squared_error' )

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Summary
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
# model.compile(optimizer=optimizer, loss=lossfn, metrics=['accuracy'])
unet_model.compile(optimizer=optimizer, loss=lossfn, metrics=[ tf.keras.metrics.RootMeanSquaredError( name='root_mean_squared_error' ) ])
# metric : rmse,


"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: FileWriter
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
if exists(checkpoint_path) :
    unet_model.load_weights(checkpoint_path)
    print("model load: " + checkpoint_path)
    input("Press Any Key!")

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Training
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
history = unet_model.fit( train_generator.flow(x_train, y_train, batch_size=1, subset='training'), epochs=5, steps_per_epoch=1 )
unet_model.save_weights(checkpoint_path)

# print( history.history )
# {'loss': [25.04973030090332], 'root_mean_squared_error': [5.004970550537109]}

plt.plot(history.history['loss'])
plt.plot(history.history['root_mean_squared_error'])
plt.legend(['loss', 'root_mean_squared_error'])
plt.autumn()
plt.show()
plt.close()

input('...')