附带可视化-visualdl
# copyright (c) 2019 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import paddle
import paddle.fluid as fluid
from paddle.fluid.param_attr import ParamAttr
__all__ = ["ResNet", "ResNet18", "ResNet34", "ResNet50", "ResNet101", "ResNet152"]
train_parameters = {
"input_size": [3, 224, 224],
"input_mean": [0.485, 0.456, 0.406],
"input_std": [0.229, 0.224, 0.225],
"learning_strategy": {
"name": "piecewise_decay",
"batch_size": 256,
"epochs": [30, 60, 90],
"steps": [0.1, 0.01, 0.001, 0.0001]
}
}
class ResNet():
def __init__(self, layers=50):
self.params = train_parameters
self.layers = layers
def net(self, input, class_dim=1000):
layers = self.layers
supported_layers = [18, 34, 50, 101, 152]
assert layers in supported_layers, \
"supported layers are {} but input layer is {}".format(supported_layers, layers)
if layers == 18:
depth = [2, 2, 2, 2]
elif layers == 34 or layers == 50:
depth = [3, 4, 6, 3]
elif layers == 101:
depth = [3, 4, 23, 3]
elif layers == 152:
depth = [3, 8, 36, 3]
num_filters = [64, 128, 256, 512]
#param_attr=fluid.initializer.Xavier(uniform=False)
conv = self.conv_bn_layer(
input=input, num_filters=64, filter_size=7, stride=2, act='relu', name="conv1")
conv = fluid.layers.pool2d(
input=conv,
pool_size=3,
pool_stride=2,
pool_padding=1,
pool_type='max')
if layers >= 50:
for block in range(len(depth)):
for i in range(depth[block]):
if layers in [101, 152] and block == 2:
if i == 0:
conv_name = "res" + str(block + 2) + "a"
else:
conv_name = "res" + str(block + 2) + "b" + str(i)
else:
conv_name = "res" + str(block + 2) + chr(97 + i)
conv = self.bottleneck_block(
input=conv,
num_filters=num_filters[block],
stride=2 if i == 0 and block != 0 else 1, name=conv_name)
pool = fluid.layers.pool2d(
input=conv, pool_size=7, pool_type='avg', global_pooling=True)
stdv = 1.0 / math.sqrt(pool.shape[1] * 1.0)
out = fluid.layers.fc(input=pool,
size=class_dim,
param_attr=fluid.param_attr.ParamAttr(
initializer=fluid.initializer.Uniform(-stdv, stdv)))
else:
for block in range(len(depth)):
for i in range(depth[block]):
conv_name = "res" + str(block + 2) + chr(97 + i)
conv = self.basic_block(
input=conv,
num_filters=num_filters[block],
stride=2 if i == 0 and block != 0 else 1,
is_first=block == i == 0,
name=conv_name)
pool = fluid.layers.pool2d(
input=conv, pool_size=7, pool_type='avg', global_pooling=True)
stdv = 1.0 / math.sqrt(pool.shape[1] * 1.0)
out = fluid.layers.fc(input=pool,
size=class_dim,
param_attr=fluid.param_attr.ParamAttr(
initializer=fluid.initializer.Uniform(-stdv, stdv)))
#self._init_params(out)
return out
def conv_bn_layer(self,
input,
num_filters,
filter_size,
stride=1,
groups=1,
act=None,
name=None):
conv = fluid.layers.conv2d(
input=input,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
act=None,
param_attr=ParamAttr(name=name + "_weights"),
bias_attr=False,
name=name + '.conv2d.output.1')
if name == "conv1":
bn_name = "bn_" + name
else:
bn_name = "bn" + name[3:]
return fluid.layers.batch_norm(input=conv,
act=act,
name=bn_name + '.output.1',
param_attr=ParamAttr(name=bn_name + '_scale'),
bias_attr=ParamAttr(bn_name + '_offset'),
moving_mean_name=bn_name + '_mean',
moving_variance_name=bn_name + '_variance', )
def shortcut(self, input, ch_out, stride, is_first, name):
ch_in = input.shape[1]
if ch_in != ch_out or stride != 1 or is_first == True:
return self.conv_bn_layer(input, ch_out, 1, stride, name=name)
else:
return input
def bottleneck_block(self, input, num_filters, stride, name):
conv0 = self.conv_bn_layer(
input=input, num_filters=num_filters, filter_size=1, act='relu', name=name + "_branch2a")
conv1 = self.conv_bn_layer(
input=conv0,
num_filters=num_filters,
filter_size=3,
stride=stride,
act='relu',
name=name + "_branch2b")
conv2 = self.conv_bn_layer(
input=conv1, num_filters=num_filters * 4, filter_size=1, act=None, name=name + "_branch2c")
short = self.shortcut(input, num_filters * 4, stride, is_first=False, name=name + "_branch1")
return fluid.layers.elementwise_add(x=short, y=conv2, act='relu', name=name + ".add.output.5")
def basic_block(self, input, num_filters, stride, is_first, name):
conv0 = self.conv_bn_layer(input=input, num_filters=num_filters, filter_size=3, act='relu', stride=stride,
name=name + "_branch2a")
conv1 = self.conv_bn_layer(input=conv0, num_filters=num_filters, filter_size=3, act=None,
name=name + "_branch2b")
short = self.shortcut(input, num_filters, stride, is_first, name=name + "_branch1")
return fluid.layers.elementwise_add(x=short, y=conv1, act='relu')
#fc = fluid.layers.fc(
# input=queries, size=10,
# param_attr=fluid.initializer.Xavier(uniform=False))
#def _init_params(self,net):
# for name, module in net.desc:
# if isinstance(module, fluid.layers.conv2d):
# module.param_attr = fluid.initializer.Xavier(uniform=False)
# if module.param_attr.bias is not None:
# fluid.initializer.ConstantInitializer(0)
def ResNet18():
model = ResNet(layers=18)
return model
def ResNet34():
model = ResNet(layers=34)
return model
def ResNet50():
model = ResNet(layers=50)
return model
def ResNet101():
model = ResNet(layers=101)
return model
def ResNet152():
model = ResNet(layers=152)
return model# -*-coding:utf-8-*-
from __future__ import print_function
import os
import argparse
from PIL import Image
import numpy
import paddle
import paddle.fluid as fluid
from visualdl import LogWriter
# 创建一个LogWriter，第一个参数是指定存放数据的路径，
# 第二个参数是指定多少次写操作执行一次内存到磁盘的数据持久化
logw = LogWriter("./paddle_log", sync_cycle=10000)
with logw.mode('train') as logger:
trainTag = logger.scalar("损失指标")#训练损失的标签 对应效果图的“train”
with logw.mode('test') as logger:
testTag = logger.scalar("损失指标")#测试损失的标签 对应效果图的“test”
import sys
class Logger(object):
def __init__(self, filename="Default.log"):
self.terminal = sys.stdout
self.log = open(filename, "a")
def write(self, message):
self.terminal.write(message)
self.log.write(message)
def flush(self):
pass
def parse_args():
parser = argparse.ArgumentParser("mnist")
parser.add_argument(
'--enable_ce',
action='store_true',
help="If set, run the task with continuous evaluation logs.")
parser.add_argument(
'--use_gpu',
type=bool,
default=True,
help="Whether to use GPU or not.")
parser.add_argument(
'--num_epochs', type=int, default=100, help="number of epochs.")
args = parser.parse_args()
return args
def loss_net(prediction, label):
#交叉熵损失函数
loss = fluid.layers.cross_entropy(input=prediction, label=label)
avg_loss = fluid.layers.mean(loss)
acc = fluid.layers.accuracy(input=prediction, label=label)
return prediction, avg_loss, acc
def multilayer_perceptron(img, label):
img = fluid.layers.fc(input=img, size=200, act='tanh')
hidden = fluid.layers.fc(input=img, size=200, act='tanh')
prediction = fluid.layers.fc(input=hidden, size=10, act='softmax')
return loss_net(prediction, label)
def softmax_regression(img, label):
prediction = fluid.layers.fc(input=img, size=10, act='softmax')
return loss_net(prediction, label)
def resnet_pre_train_10class(img, label):
import resnet
prediction = resnet.ResNet18().net(input=img, class_dim=10)
#resnet50中的最后fc层没有使用激活函数softmax，应该加上然后使用交叉熵损失函数
prediction_softmax = fluid.layers.softmax(input=prediction, use_cudnn=True)
return loss_net(prediction_softmax, label)
#-------训练期间通过调用一个handler函数来监控训练进度---------
from paddle.utils.plot import Ploter
train_prompt = "Train cost"
test_prompt = "Test cost"
cost_ploter = Ploter(train_prompt, test_prompt)
# 将训练过程绘图表示
def event_handler_plot(ploter_title, step, cost):
cost_ploter.append(ploter_title, step, cost)
cost_ploter.plot("./plot/paddle_plot")
# 打印训练的中间结果，训练轮次，batch数，损失函数
def event_handler(pass_id, batch_id, cost):
print("Pass %d, Batch %d, Cost %f" % (pass_id,batch_id, cost))
def train(nn_type,
use_cuda,
save_dirname=None,
model_filename=None,
params_filename=None):
#不理解啥意思，因为函数返回为false所以一定会继续执行,可能判断是否paddle安装或者编译成功
if use_cuda and not fluid.core.is_compiled_with_cuda():
return
#定义了创建模型参数，输入输出，以及模型中可学习参数的初始化等各种操作
startup_program = fluid.default_startup_program()
#定义了神经网络模型，前向反向计算，以及优化算法对网络中可学习参数的更新
main_program = fluid.default_main_program()
#是否固定random_seed,即是否保证模型可复现，通过打印出的acc，avg等验证
if args.enable_ce:
train_reader = paddle.batch(
paddle.dataset.mnist.train(), batch_size=BATCH_SIZE)
test_reader = paddle.batch(
paddle.dataset.mnist.test(), batch_size=BATCH_SIZE)
startup_program.random_seed = 90
main_program.random_seed = 90
#数据提取操作，提取-打乱-打包batch
else:
train_reader = paddle.batch(
paddle.reader.shuffle(paddle.dataset.mnist.train(), buf_size=500),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
paddle.dataset.mnist.test(), batch_size=BATCH_SIZE)
#定义网络输入，image and label
img = fluid.layers.data(name='img', shape=[1, 28, 28], dtype='float32')
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
#选择网络主干
if nn_type == 'softmax_regression':
net_conf = softmax_regression
elif nn_type == 'multilayer_perceptron':
net_conf = multilayer_perceptron
else:
net_conf = resnet_pre_train_10class
#网络组合，输入(image+label)+主干+loss(loss类型,以及输出的loss格式-平均avg和准确率)
prediction, avg_loss, acc = net_conf(img, label)
#程序克隆-#定义了神经网络模型，前向反向计算，以及优化算法对网络中可学习参数的更新
test_program = main_program.clone(for_test=True)
#选择优化器
optimizer = fluid.optimizer.Adam(learning_rate=0.001)
#选择优化目标-avg_loss
optimizer.minimize(avg_loss)
#提前定义好测试函数 在训练时候使用
def train_test(train_test_program, train_test_feed, train_test_reader):
#test_program通过main_program进行克隆，防止混淆，因为主程序中有梯度等参数
acc_set = []
avg_loss_set = []
for test_data in train_test_reader():
acc_np, avg_loss_np = exe.run(
program=train_test_program,
feed=train_test_feed.feed(test_data),
fetch_list=[acc, avg_loss])
acc_set.append(float(acc_np))
avg_loss_set.append(float(avg_loss_np))
# get test acc and loss
acc_val_mean = numpy.array(acc_set).mean()
avg_loss_val_mean = numpy.array(avg_loss_set).mean()
#返回全部测试集的平均loss和平均准确率
return avg_loss_val_mean, acc_val_mean
#place属性由用户定义，代表程序将在哪里执行
place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
#创建一个Executor执行器
exe = fluid.Executor(place)
#定义DataFeeder数据读取器,网络读取方式，指定网络的输入(网络通过graph搭建，需要指定输入)
feeder = fluid.DataFeeder(feed_list=[img, label], place=place)
#这里需要注意，在初始化前，把loss，优化器，执行器等都要定义好
#正式进行网络训练前，需先执行参数初始化。其中 defalut_startup_program 中定义了创建模型参数，输入输出，以及模型中可学习参数的初始化等各种操作。
exe.run(startup_program)
#训练epochs次数
epochs = [epoch_id for epoch_id in range(PASS_NUM)]
#list用于保存 epoch_id, avg_loss_val, acc_val
lists = []
step = 0
#epochs循环操作
for epoch_id in epochs:
# train_reader数据输入
for step_id, data in enumerate(train_reader()):
#由于传入数据与传出数据存在多列，因此 fluid 通过 feed 映射定义数据的传输数据，
#通过 fetch_list 取出期望结果：
metrics = exe.run(
main_program,
feed=feeder.feed(data),
fetch_list=[avg_loss, acc])
#若batch提取次数为100，画出loss曲线，打印出avg_loss等参数
if step % 100 == 0:
event_handler_plot(train_prompt, step, metrics[0])
print("Pass %d, Epoch %d, Cost %f" % (step, epoch_id, metrics[0]))
step += 1
#paddle-visualdl #输入数据
trainTag.add_record(step, metrics[0])
#每迭代一次，进行一次测试工作
# test for epoch
avg_loss_val, acc_val = train_test(
train_test_program=test_program,
train_test_reader=test_reader,
train_test_feed=feeder)
#打印epoch测试结果
print("Test with Epoch %d, avg_cost: %s, acc: %s" % (epoch_id, avg_loss_val, acc_val))
#输出loss图-avg_loss
event_handler_plot(test_prompt, step, avg_loss_val)
#paddle-visualdl #输入数据
testTag.add_record(step, avg_loss_val)
#保存每次测试结果，方便后续找到最优测试结果
lists.append((epoch_id, avg_loss_val, acc_val))
#如果给定路径，每次epoch都保存模型且覆盖之前的模型
#保存模型时候应该指定输入input--["img"]
#["img"]--预测（inference）需要 feed 的数据
#[prediction]--保存预测（inference）结果的 Variables
#exe--executor 保存 inference model
if save_dirname is not None:
fluid.io.save_inference_model(
save_dirname, ["img"], [prediction],
exe,
model_filename=model_filename,
params_filename=params_filename)
#epochs迭代完毕
#模型可复现，打印出训练的avg_loss，测试的avg_loss_val和acc_val
if args.enable_ce:
print("kpis\ttrain_cost\t%f" % metrics[0])
print("kpis\ttest_cost\t%s" % avg_loss_val)
print("kpis\ttest_acc\t%s" % acc_val)
#找到最优的测试结果，打印出最优结果 epoch_id avg_loss_val
# find the best pass
best = sorted(lists, key=lambda list: float(list[1]))[0]
print('Best pass is %s, testing Avgcost is %s' % (best[0], best[1]))
#打印分类的最优准确率
print('The classification accuracy is %.2f%%' % (float(best[2]) * 100))
def infer(use_cuda,
save_dirname=None,
model_filename=None,
params_filename=None):
#网络是否保存了模型
if save_dirname is None:
return
#place属性由用户定义，代表程序将在哪里执行 cpu or gpu
place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
#定义执行器
exe = fluid.Executor(place)
#定义图像载入函数 通过PIL打开，resize到网络输入大小，进行归一化操作
#定义N×C×H×W and float32
#这些操作在mnist中已经定义，所以预测要一样
def load_image(file):
im = Image.open(file).convert('L')
im = im.resize((28, 28), Image.ANTIALIAS)
im = numpy.array(im).reshape(1, 1, 28, 28).astype(numpy.float32)
im = im / 255.0 * 2.0 - 1.0
return im
#获取当前程序运行路径
cur_dir = os.path.dirname(os.path.realpath(__file__))
#载入测试图像
tensor_img = load_image(cur_dir + '/image/mnist_train_20.png')
inference_scope = fluid.core.Scope()
with fluid.scope_guard(inference_scope):
# Use fluid.io.load_inference_model to obtain the inference program desc,
# the feed_target_names (the names of variables that will be feeded
# data using feed operators), and the fetch_targets (variables that
# we want to obtain data from using fetch operators).
#载入模型
#返回：(Program，feed_target_names, fetch_targets)
#Program 是一个 Program ，它是预测 Program。
#feed_target_names 是一个str列表，它包含需要在预测 Program 中提供数据的变量的名称。
#fetch_targets 是一个 Variable 列表，从中我们可以得到推断结果。
[inference_program, feed_target_names, fetch_targets] = fluid.io.load_inference_model(
save_dirname, exe, model_filename, params_filename)
# Construct feed as a dictionary of {feed_target_name: feed_target_data}
# and results will contain a list of data corresponding to fetch_targets.
#下列操作对应训练阶段的
'''
metrics = exe.run(
main_program,
feed=feeder.feed(data),
fetch_list=[avg_loss, acc])
'''
results = exe.run(
inference_program,
feed={feed_target_names[0]: tensor_img},
fetch_list=fetch_targets)
#results=list[array([list[1,2,3,4,5,6,7,8,9,10]])]
#按升序排列
#所以lab[0][0][-1]
lab = numpy.argsort(results)
print("Inference result of image/mnist_train_20.png is: %d" % lab[0][0][-1])
def main(use_cuda, nn_type):
# 保存参数，若为None，则默认为： __model__
#model_filename = None
model_filename = "paddle_model"
#保存参数，若为None，则保存为分离状态的参数 batch_norm_0.b_0 conv2d_0.b_0 等等
#params_filename = None
params_filename = "paddle_params"
#参数和模型的保存路径
save_dirname = "recognize_digits_" + nn_type + ".inference.model"
#保存所有print输出到log文件
sys.stdout = Logger('paddle_log.txt')
# call train() with is_local argument to run distributed train
#训练程序和测试程序
train(
nn_type=nn_type,
use_cuda=use_cuda,
save_dirname=save_dirname,
model_filename=model_filename,
params_filename=params_filename)
#使用保存的模型前向传播测试
infer(
use_cuda=use_cuda,
save_dirname=save_dirname,
model_filename=model_filename,
params_filename=params_filename)
if __name__ == '__main__':
#定义输入args参数
args = parse_args()
BATCH_SIZE = 64
PASS_NUM = args.num_epochs
use_cuda = args.use_gpu
# predict = 'softmax_regression' # uncomment for Softmax
# predict = 'multilayer_perceptron' # uncomment for MLP
#选择使用的主干网络
predict = 'convolutional_neural_network' # uncomment for LeNet5
main(use_cuda=use_cuda, nn_type=predict)
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
