项目简介
本项目基于paddle 实现了图像分类模型 DenseNet，建议使用GPU运行。动态图版本请查看：用PaddlePaddle实现图像分类-DenseNet（动态图版）
下载安装命令
## CPU版本安装命令
pip install -f https://paddlepaddle.org.cn/pip/oschina/cpu paddlepaddle
## GPU版本安装命令
pip install -f https://paddlepaddle.org.cn/pip/oschina/gpu paddlepaddle-gpu In[1]
# 解压花朵数据集
!cd data/data2815 && unzip -qo flower_photos.zip In[2]
# !export FLAGS_fraction_of_gpu_memory_to_use=0.9
# !echo $FLAGS_fraction_of_gpu_memory_to_use In[2]
# 预处理数据，将其转化为标准格式。同时将数据拆分成两份，以便训练和计算预估准确率
import codecs
import os
import random
import shutil
from PIL import Image
train_ratio = 4.0/ 5
all_file_dir = 'data/data2815'
class_list = [c for c in os.listdir(all_file_dir) if os.path.isdir(os.path.join(all_file_dir, c)) and not c.endswith('Set') and not c.startswith('.')]
class_list.sort()
print(class_list)
train_image_dir = os.path.join(all_file_dir, "trainImageSet")
if not os.path.exists(train_image_dir):
os.makedirs(train_image_dir)
eval_image_dir = os.path.join(all_file_dir, "evalImageSet")
if not os.path.exists(eval_image_dir):
os.makedirs(eval_image_dir)
train_file = codecs.open(os.path.join(all_file_dir, "train.txt"), 'w')
eval_file = codecs.open(os.path.join(all_file_dir, "eval.txt"), 'w')
with codecs.open(os.path.join(all_file_dir, "label_list.txt"), "w") as label_list:
label_id = 0
for class_dir in class_list:
label_list.write("{0}\t{1}\n".format(label_id, class_dir))
image_path_pre = os.path.join(all_file_dir, class_dir)
for file in os.listdir(image_path_pre):
try:
img = Image.open(os.path.join(image_path_pre, file))
if random.uniform(0, 1) <= train_ratio:
shutil.copyfile(os.path.join(image_path_pre, file), os.path.join(train_image_dir, file))
train_file.write("{0}\t{1}\n".format(os.path.join(train_image_dir, file), label_id))
else:
shutil.copyfile(os.path.join(image_path_pre, file), os.path.join(eval_image_dir, file))
eval_file.write("{0}\t{1}\n".format(os.path.join(eval_image_dir, file), label_id))
except Exception as e:
pass
# 存在一些文件打不开，此处需要稍作清洗
label_id += 1
train_file.close()
eval_file.close()['daisy', 'dandelion', 'roses', 'sunflowers', 'tulips']
In[3]
# -*- coding: UTF-8 -*-
"""
训练常用视觉基础网络，用于分类任务
需要将训练图片，类别文件 label_list.txt 放置在同一个文件夹下
程序会先读取 train.txt 文件获取类别数和图片数量
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
os.environ['FLAGS_eager_delete_tensor_gb'] = '0'
os.environ['FLAGS_fraction_of_gpu_memory_to_use'] = '0.75'
import numpy as np
import time
import math
import paddle
import paddle.fluid as fluid
import codecs
import logging
from paddle.fluid.initializer import MSRA
from paddle.fluid.initializer import Uniform
from paddle.fluid.param_attr import ParamAttr
from PIL import Image
from PIL import ImageEnhance
train_parameters = {
"input_size": [3, 512, 512],
"class_dim": -1, # 分类数，会在初始化自定义 reader 的时候获得
"image_count": -1, # 训练图片数量，会在初始化自定义 reader 的时候获得
"label_dict": {},
"data_dir": "data/data2815", # 训练数据存储地址
"train_file_list": "train.txt",
"label_file": "label_list.txt",
"save_freeze_dir": "./freeze-model",
"save_persistable_dir": "./persistable-params",
"continue_train": True, # 是否接着上一次保存的参数接着训练，优先级高于预训练模型
"pretrained": False, # 是否使用预训练的模型
"pretrained_dir": "data/data6593/DenseNet_pretrained",
"mode": "train",
"num_epochs": 1,
"train_batch_size": 8,
"mean_rgb": [127.5, 127.5, 127.5], # 常用图片的三通道均值，通常来说需要先对训练数据做统计，此处仅取中间值
"use_gpu": True,
"dropout_prob": 0.2,
"dropout_seed": None,
"image_enhance_strategy": { # 图像增强相关策略
"need_distort": True, # 是否启用图像颜色增强
"need_rotate": True, # 是否需要增加随机角度
"need_crop": True, # 是否要增加裁剪
"need_flip": True, # 是否要增加水平随机翻转
"hue_prob": 0.5,
"hue_delta": 18,
"contrast_prob": 0.5,
"contrast_delta": 0.5,
"saturation_prob": 0.5,
"saturation_delta": 0.5,
"brightness_prob": 0.5,
"brightness_delta": 0.125,
"rotate_prob": 0.5,
"rotate_range": 14
},
"early_stop": {
"sample_frequency": 50,
"successive_limit": 5,
"good_acc1": 0.92
},
"rsm_strategy": {
"learning_rate": 0.001,
"lr_epochs": [20, 40, 60, 80, 100],
"lr_decay": [1, 0.5, 0.25, 0.1, 0.05, 0.01]
}
}
class DenseNet():
def __init__(self, layers, dropout_prob):
self.layers = layers
self.dropout_prob = dropout_prob
def bottleneck_layer(self, input, fliter_num, name):
bn = fluid.layers.batch_norm(input=input, act='relu', name=name + '_bn1')
conv1 = fluid.layers.conv2d(input=bn, num_filters=fliter_num * 4, filter_size=1, name=name + '_conv1')
dropout = fluid.layers.dropout(x=conv1, dropout_prob=self.dropout_prob)
bn = fluid.layers.batch_norm(input=dropout, act='relu', name=name + '_bn2')
conv2 = fluid.layers.conv2d(input=bn, num_filters=fliter_num, filter_size=3, padding=1, name=name + '_conv2')
dropout = fluid.layers.dropout(x=conv2, dropout_prob=self.dropout_prob)
return dropout
def dense_block(self, input, block_num, fliter_num, name):
layers = []
layers.append(input)#拼接到列表
x = self.bottleneck_layer(input, fliter_num, name=name + '_bottle_' + str(0))
layers.append(x)
for i in range(block_num - 1):
x = paddle.fluid.layers.concat(layers, axis=1)
x = self.bottleneck_layer(x, fliter_num, name=name + '_bottle_' + str(i + 1))
layers.append(x)
return paddle.fluid.layers.concat(layers, axis=1)
def transition_layer(self, input, fliter_num, name):
bn = fluid.layers.batch_norm(input=input, act='relu', name=name + '_bn1')
conv1 = fluid.layers.conv2d(input=bn, num_filters=fliter_num, filter_size=1, name=name + '_conv1')
dropout = fluid.layers.dropout(x=conv1, dropout_prob=self.dropout_prob)
return fluid.layers.pool2d(input=dropout, pool_size=2, pool_type='avg', pool_stride=2)
def net(self, input, class_dim=1000):
layer_count_dict = {
121: (32, [6, 12, 24, 16]),
169: (32, [6, 12, 32, 32]),
201: (32, [6, 12, 48, 32]),
161: (48, [6, 12, 36, 24])
}
layer_conf = layer_count_dict[self.layers]
conv = fluid.layers.conv2d(input=input, num_filters=layer_conf[0] * 2,
filter_size=7, stride=2, padding=3, name='densenet_conv0')
conv = fluid.layers.pool2d(input=conv, pool_size=3, pool_padding=1, pool_type='max', pool_stride=2)
for i in range(len(layer_conf[1]) - 1):
conv = self.dense_block(conv, layer_conf[1][i], layer_conf[0], 'dense_' + str(i))
conv = self.transition_layer(conv, layer_conf[0], name='trans_' + str(i))
conv = self.dense_block(conv, layer_conf[1][-1], layer_conf[0], 'dense_' + str(len(layer_conf[1])))
conv = fluid.layers.pool2d(input=conv, global_pooling=True, pool_type='avg')
out = fluid.layers.fc(conv, class_dim, act='softmax')
# last fc layer is "out"
return out
def init_log_config():
"""
初始化日志相关配置
:return:
"""
global logger
logger = logging.getLogger()
logger.setLevel(logging.INFO)
log_path = os.path.join(os.getcwd(), 'logs')
if not os.path.exists(log_path):
os.makedirs(log_path)
log_name = os.path.join(log_path, 'train.log')
sh = logging.StreamHandler()
fh = logging.FileHandler(log_name, mode='w')
fh.setLevel(logging.DEBUG)
formatter = logging.Formatter("%(asctime)s - %(filename)s[line:%(lineno)d] - %(levelname)s: %(message)s")
fh.setFormatter(formatter)
sh.setFormatter(formatter)
logger.addHandler(sh)
logger.addHandler(fh)
def init_train_parameters():
"""
初始化训练参数，主要是初始化图片数量，类别数
:return:
"""
train_file_list = os.path.join(train_parameters['data_dir'], train_parameters['train_file_list'])
label_list = os.path.join(train_parameters['data_dir'], train_parameters['label_file'])
index = 0
with codecs.open(label_list, encoding='utf-8') as flist:
lines = [line.strip() for line in flist]
for line in lines:
parts = line.strip().split()
train_parameters['label_dict'][parts[1]] = int(parts[0])
index += 1
train_parameters['class_dim'] = index
with codecs.open(train_file_list, encoding='utf-8') as flist:
lines = [line.strip() for line in flist]
train_parameters['image_count'] = len(lines)
def resize_img(img, target_size):
"""
强制缩放图片
:param img:
:param target_size:
:return:
"""
target_size = input_size
img = img.resize((target_size[1], target_size[2]), Image.BILINEAR)
return img
def random_crop(img, scale=[0.08, 1.0], ratio=[3. / 4., 4. / 3.]):
aspect_ratio = math.sqrt(np.random.uniform(*ratio))
w = 1. * aspect_ratio
h = 1. / aspect_ratio
bound = min((float(img.size[0]) / img.size[1]) / (w**2),
(float(img.size[1]) / img.size[0]) / (h**2))
scale_max = min(scale[1], bound)
scale_min = min(scale[0], bound)
target_area = img.size[0] * img.size[1] * np.random.uniform(scale_min,
scale_max)
target_size = math.sqrt(target_area)
w = int(target_size * w)
h = int(target_size * h)
i = np.random.randint(0, img.size[0] - w + 1)
j = np.random.randint(0, img.size[1] - h + 1)
img = img.crop((i, j, i + w, j + h))
img = img.resize((train_parameters['input_size'][1], train_parameters['input_size'][2]), Image.BILINEAR)
return img
def rotate_image(img):
"""
图像增强，增加随机旋转角度
"""
prob = np.random.uniform(0, 1)
if prob < train_parameters['image_enhance_strategy']['rotate_prob']:
range = train_parameters['image_enhance_strategy']['rotate_range']
angle = np.random.randint(-range, range)
img = img.rotate(angle)
return img
def random_brightness(img):
"""
图像增强，亮度调整
:param img:
:return:
"""
prob = np.random.uniform(0, 1)
if prob < train_parameters['image_enhance_strategy']['brightness_prob']:
brightness_delta = train_parameters['image_enhance_strategy']['brightness_delta']
delta = np.random.uniform(-brightness_delta, brightness_delta) + 1
img = ImageEnhance.Brightness(img).enhance(delta)
return img
def random_contrast(img):
"""
图像增强，对比度调整
:param img:
:return:
"""
prob = np.random.uniform(0, 1)
if prob < train_parameters['image_enhance_strategy']['contrast_prob']:
contrast_delta = train_parameters['image_enhance_strategy']['contrast_delta']
delta = np.random.uniform(-contrast_delta, contrast_delta) + 1
img = ImageEnhance.Contrast(img).enhance(delta)
return img
def random_saturation(img):
"""
图像增强，饱和度调整
:param img:
:return:
"""
prob = np.random.uniform(0, 1)
if prob < train_parameters['image_enhance_strategy']['saturation_prob']:
saturation_delta = train_parameters['image_enhance_strategy']['saturation_delta']
delta = np.random.uniform(-saturation_delta, saturation_delta) + 1
img = ImageEnhance.Color(img).enhance(delta)
return img
def random_hue(img):
"""
图像增强，色度调整
:param img:
:return:
"""
prob = np.random.uniform(0, 1)
if prob < train_parameters['image_enhance_strategy']['hue_prob']:
hue_delta = train_parameters['image_enhance_strategy']['hue_delta']
delta = np.random.uniform(-hue_delta, hue_delta)
img_hsv = np.array(img.convert('HSV'))
img_hsv[:, :, 0] = img_hsv[:, :, 0] + delta
img = Image.fromarray(img_hsv, mode='HSV').convert('RGB')
return img
def distort_color(img):
"""
概率的图像增强
:param img:
:return:
"""
prob = np.random.uniform(0, 1)
# Apply different distort order
if prob < 0.35:
img = random_brightness(img)
img = random_contrast(img)
img = random_saturation(img)
img = random_hue(img)
elif prob < 0.7:
img = random_brightness(img)
img = random_saturation(img)
img = random_hue(img)
img = random_contrast(img)
return img
def custom_image_reader(file_list, data_dir, mode):
"""
自定义用户图片读取器，先初始化图片种类，数量
:param file_list:
:param data_dir:
:param mode:
:return:
"""
with codecs.open(file_list) as flist:
lines = [line.strip() for line in flist]
def reader():
np.random.shuffle(lines)
for line in lines:
if mode == 'train' or mode == 'val':
img_path, label = line.split()
img = Image.open(img_path)
try:
if img.mode != 'RGB':
img = img.convert('RGB')
if train_parameters['image_enhance_strategy']['need_distort'] == True:
img = distort_color(img)
if train_parameters['image_enhance_strategy']['need_rotate'] == True:
img = rotate_image(img)
if train_parameters['image_enhance_strategy']['need_crop'] == True:
img = random_crop(img, train_parameters['input_size'])
if train_parameters['image_enhance_strategy']['need_flip'] == True:
mirror = int(np.random.uniform(0, 2))
if mirror == 1:
img = img.transpose(Image.FLIP_LEFT_RIGHT)
# HWC--->CHW && normalized
img = np.array(img).astype('float32')
img -= train_parameters['mean_rgb']
img = img.transpose((2, 0, 1)) # HWC to CHW
img *= 0.007843 # 像素值归一化
yield img, int(label)
except Exception as e:
pass # 以防某些图片读取处理出错，加异常处理
elif mode == 'test':
img_path = os.path.join(data_dir, line)
img = Image.open(img_path)
if img.mode != 'RGB':
img = img.convert('RGB')
img = resize_img(img, train_parameters['input_size'])
# HWC--->CHW && normalized
img = np.array(img).astype('float32')
img -= train_parameters['mean_rgb']
img = img.transpose((2, 0, 1)) # HWC to CHW
img *= 0.007843 # 像素值归一化
yield img
return reader
def optimizer_rms_setting():
"""
阶梯型的学习率适合比较大规模的训练数据
"""
batch_size = train_parameters["train_batch_size"]
iters = train_parameters["image_count"] // batch_size
learning_strategy = train_parameters['rsm_strategy']
lr = learning_strategy['learning_rate']
boundaries = [i * iters for i in learning_strategy["lr_epochs"]]
values = [i * lr for i in learning_strategy["lr_decay"]]
optimizer = fluid.optimizer.RMSProp(
learning_rate=fluid.layers.piecewise_decay(boundaries, values))
return optimizer
def load_params(exe, program):
if train_parameters['continue_train'] and os.path.exists(train_parameters['save_persistable_dir']):
logger.info('load params from retrain model')
fluid.io.load_persistables(executor=exe,
dirname=train_parameters['save_persistable_dir'],
main_program=program)
elif train_parameters['pretrained'] and os.path.exists(train_parameters['pretrained_dir']):
logger.info('load params from pretrained model')
def if_exist(var):
return os.path.exists(os.path.join(train_parameters['pretrained_dir'], var.name))
fluid.io.load_vars(exe, train_parameters['pretrained_dir'], main_program=program,
predicate=if_exist)
def train():
train_prog = fluid.Program()
train_startup = fluid.Program()
logger.info("create prog success")
logger.info("train config: %s", str(train_parameters))
logger.info("build input custom reader and data feeder")
file_list = os.path.join(train_parameters['data_dir'], "train.txt")
mode = train_parameters['mode']
batch_reader = paddle.batch(custom_image_reader(file_list, train_parameters['data_dir'], mode),
batch_size=train_parameters['train_batch_size'],
drop_last=False)
batch_reader = paddle.reader.shuffle(batch_reader, train_parameters['train_batch_size'])
place = fluid.CUDAPlace(0) if train_parameters['use_gpu'] else fluid.CPUPlace()
# 定义输入数据的占位符
img = fluid.layers.data(name='img', shape=train_parameters['input_size'], dtype='float32')
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
feeder = fluid.DataFeeder(feed_list=[img, label], place=place)
# 选取不同的网络
logger.info("build newwork")
model = DenseNet(121, train_parameters['dropout_prob'])
out = model.net(input=img, class_dim=train_parameters['class_dim'])
cost = fluid.layers.cross_entropy(input=out, label=label)
avg_cost = fluid.layers.mean(x=cost)
acc_top1 = fluid.layers.accuracy(input=out, label=label, k=1)
optimizer = optimizer_rms_setting()
optimizer.minimize(avg_cost)
exe = fluid.Executor(place)
main_program = fluid.default_main_program()
exe.run(fluid.default_startup_program())
train_fetch_list = [avg_cost.name, acc_top1.name, out.name]
load_params(exe, main_program)
# 训练循环主体
stop_strategy = train_parameters['early_stop']
successive_limit = stop_strategy['successive_limit']
sample_freq = stop_strategy['sample_frequency']
good_acc1 = stop_strategy['good_acc1']
successive_count = 0
stop_train = False
total_batch_count = 0
for pass_id in range(train_parameters["num_epochs"]):
logger.info("current pass: %d, start read image", pass_id)
batch_id = 0
for step_id, data in enumerate(batch_reader()):
t1 = time.time()
loss, acc1, pred_ot = exe.run(main_program,
feed=feeder.feed(data),
fetch_list=train_fetch_list)
t2 = time.time()
batch_id += 1
total_batch_count += 1
period = t2 - t1
loss = np.mean(np.array(loss))
acc1 = np.mean(np.array(acc1))
if batch_id % 10 == 0:
logger.info("Pass {0}, trainbatch {1}, loss {2}, acc1 {3}, time {4}".format(pass_id, batch_id, loss, acc1,
"%2.2f sec" % period))
# 简单的提前停止策略，认为连续达到某个准确率就可以停止了
if acc1 >= good_acc1:
successive_count += 1
logger.info("current acc1 {0} meets good {1}, successive count {2}".format(acc1, good_acc1, successive_count))
fluid.io.save_inference_model(dirname=train_parameters['save_freeze_dir'],
feeded_var_names=['img'],
target_vars=[out],
main_program=main_program,
executor=exe)
if successive_count >= successive_limit:
logger.info("end training")
stop_train = True
break
else:
successive_count = 0
# 通用的保存策略，减小意外停止的损失
if total_batch_count % sample_freq == 0:
logger.info("temp save {0} batch train result, current acc1 {1}".format(total_batch_count, acc1))
fluid.io.save_persistables(dirname=train_parameters['save_persistable_dir'],
main_program=main_program,
executor=exe)
if stop_train:
break
logger.info("training till last epcho, end training")
fluid.io.save_persistables(dirname=train_parameters['save_persistable_dir'],
main_program=main_program,
executor=exe)
fluid.io.save_inference_model(dirname=train_parameters['save_freeze_dir'],
feeded_var_names=['img'],
target_vars=[out],
main_program=main_program,
executor=exe)
if __name__ == '__main__':
init_log_config()
init_train_parameters()
train()2020-02-04 13:22:15,398 - <ipython-input-3-59b2da92959c>[line:395] - INFO: create prog success
2020-02-04 13:22:15,400 - <ipython-input-3-59b2da92959c>[line:396] - INFO: train config: {'input_size': [3, 512, 512], 'class_dim': 5, 'image_count': 2932, 'label_dict': {'daisy': 0, 'dandelion': 1, 'roses': 2, 'sunflowers': 3, 'tulips': 4}, 'data_dir': 'data/data2815', 'train_file_list': 'train.txt', 'label_file': 'label_list.txt', 'save_freeze_dir': './freeze-model', 'save_persistable_dir': './persistable-params', 'continue_train': True, 'pretrained': False, 'pretrained_dir': 'data/data6593/DenseNet_pretrained', 'mode': 'train', 'num_epochs': 1, 'train_batch_size': 8, 'mean_rgb': [127.5, 127.5, 127.5], 'use_gpu': True, 'dropout_prob': 0.2, 'dropout_seed': None, 'image_enhance_strategy': {'need_distort': True, 'need_rotate': True, 'need_crop': True, 'need_flip': True, 'hue_prob': 0.5, 'hue_delta': 18, 'contrast_prob': 0.5, 'contrast_delta': 0.5, 'saturation_prob': 0.5, 'saturation_delta': 0.5, 'brightness_prob': 0.5, 'brightness_delta': 0.125, 'rotate_prob': 0.5, 'rotate_range': 14}, 'early_stop': {'sample_frequency': 50, 'successive_limit': 5, 'good_acc1': 0.92}, 'rsm_strategy': {'learning_rate': 0.001, 'lr_epochs': [20, 40, 60, 80, 100], 'lr_decay': [1, 0.5, 0.25, 0.1, 0.05, 0.01]}}
2020-02-04 13:22:15,401 - <ipython-input-3-59b2da92959c>[line:397] - INFO: build input custom reader and data feeder
2020-02-04 13:22:15,404 - <ipython-input-3-59b2da92959c>[line:411] - INFO: build newwork
2020-02-04 13:22:21,768 - <ipython-input-3-59b2da92959c>[line:379] - INFO: load params from retrain model
2020-02-04 13:22:22,996 - <ipython-input-3-59b2da92959c>[line:437] - INFO: current pass: 0, start read image
2020-02-04 13:22:29,206 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 10, loss 0.9336051940917969, acc1 0.625, time 0.37 sec
2020-02-04 13:22:34,591 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 20, loss 1.3102086782455444, acc1 0.375, time 0.72 sec
2020-02-04 13:22:39,732 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 30, loss 0.8531516790390015, acc1 0.75, time 0.37 sec
2020-02-04 13:22:45,115 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 40, loss 0.8436557054519653, acc1 0.875, time 0.71 sec
2020-02-04 13:22:51,210 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 50, loss 0.7807086110115051, acc1 0.75, time 0.37 sec
2020-02-04 13:22:51,216 - <ipython-input-3-59b2da92959c>[line:471] - INFO: temp save 50 batch train result, current acc1 0.75
2020-02-04 13:23:16,851 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 60, loss 1.6263551712036133, acc1 0.25, time 0.38 sec
2020-02-04 13:23:21,998 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 70, loss 2.2562952041625977, acc1 0.25, time 0.37 sec
2020-02-04 13:23:27,388 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 80, loss 0.6658831238746643, acc1 0.875, time 0.37 sec
2020-02-04 13:23:33,463 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 90, loss 1.5621132850646973, acc1 0.25, time 0.37 sec
2020-02-04 13:23:34,201 - <ipython-input-3-59b2da92959c>[line:456] - INFO: current acc1 1.0 meets good 0.92, successive count 1
2020-02-04 13:23:48,063 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 100, loss 1.4536634683609009, acc1 0.5, time 0.38 sec
2020-02-04 13:23:48,069 - <ipython-input-3-59b2da92959c>[line:471] - INFO: temp save 100 batch train result, current acc1 0.5
2020-02-04 13:24:00,505 - <ipython-input-3-59b2da92959c>[line:456] - INFO: current acc1 1.0 meets good 0.92, successive count 1
2020-02-04 13:24:17,550 - <ipython-input-3-59b2da92959c>[line:456] - INFO: current acc1 1.0 meets good 0.92, successive count 2
2020-02-04 13:24:33,818 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 110, loss 1.1879881620407104, acc1 0.625, time 0.37 sec
2020-02-04 13:24:38,354 - <ipython-input-3-59b2da92959c>[line:456] - INFO: current acc1 1.0 meets good 0.92, successive count 1
2020-02-04 13:24:42,509 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 120, loss 1.4731115102767944, acc1 0.75, time 0.37 sec
2020-02-04 13:24:48,811 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 130, loss 1.01566743850708, acc1 0.625, time 0.36 sec
2020-02-04 13:24:54,207 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 140, loss 1.2538089752197266, acc1 0.5, time 0.38 sec
2020-02-04 13:24:59,186 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 150, loss 1.099663257598877, acc1 0.625, time 0.36 sec
2020-02-04 13:24:59,191 - <ipython-input-3-59b2da92959c>[line:471] - INFO: temp save 150 batch train result, current acc1 0.625
2020-02-04 13:25:11,243 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 160, loss 0.7709023952484131, acc1 0.75, time 0.38 sec
2020-02-04 13:25:17,470 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 170, loss 1.950009822845459, acc1 0.25, time 0.37 sec
2020-02-04 13:25:22,876 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 180, loss 1.2726645469665527, acc1 0.5, time 0.38 sec
2020-02-04 13:25:27,933 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 190, loss 0.8911234736442566, acc1 0.5, time 0.37 sec
2020-02-04 13:25:33,270 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 200, loss 1.3178355693817139, acc1 0.5, time 0.36 sec
2020-02-04 13:25:33,275 - <ipython-input-3-59b2da92959c>[line:471] - INFO: temp save 200 batch train result, current acc1 0.5
2020-02-04 13:25:43,080 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 210, loss 1.1517680883407593, acc1 0.375, time 0.37 sec
2020-02-04 13:25:48,461 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 220, loss 0.9460452795028687, acc1 0.625, time 0.37 sec
2020-02-04 13:25:53,338 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 230, loss 1.156903624534607, acc1 0.625, time 0.35 sec
2020-02-04 13:25:55,666 - <ipython-input-3-59b2da92959c>[line:456] - INFO: current acc1 1.0 meets good 0.92, successive count 1
2020-02-04 13:26:00,953 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 240, loss 1.087732195854187, acc1 0.5, time 0.40 sec
2020-02-04 13:26:08,404 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 250, loss 0.5304011702537537, acc1 0.75, time 0.42 sec
2020-02-04 13:26:08,410 - <ipython-input-3-59b2da92959c>[line:471] - INFO: temp save 250 batch train result, current acc1 0.75
2020-02-04 13:26:18,023 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 260, loss 1.483151912689209, acc1 0.375, time 0.70 sec
2020-02-04 13:26:23,112 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 270, loss 1.3894118070602417, acc1 0.375, time 0.37 sec
2020-02-04 13:26:28,520 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 280, loss 1.3526442050933838, acc1 0.375, time 0.69 sec
2020-02-04 13:26:34,688 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 290, loss 0.9283148050308228, acc1 0.5, time 0.37 sec
2020-02-04 13:26:39,846 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 300, loss 1.6060166358947754, acc1 0.5, time 0.37 sec
2020-02-04 13:26:39,852 - <ipython-input-3-59b2da92959c>[line:471] - INFO: temp save 300 batch train result, current acc1 0.5
2020-02-04 13:26:48,930 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 310, loss 0.8506236672401428, acc1 0.75, time 0.37 sec
2020-02-04 13:26:54,474 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 320, loss 1.5631606578826904, acc1 0.375, time 0.73 sec
2020-02-04 13:27:00,773 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 330, loss 0.9395308494567871, acc1 0.625, time 0.37 sec
2020-02-04 13:27:04,778 - <ipython-input-3-59b2da92959c>[line:456] - INFO: current acc1 1.0 meets good 0.92, successive count 1
2020-02-04 13:27:11,766 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 340, loss 0.8109387755393982, acc1 0.625, time 0.37 sec
2020-02-04 13:27:17,388 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 350, loss 1.0135769844055176, acc1 0.5, time 0.75 sec
2020-02-04 13:27:17,391 - <ipython-input-3-59b2da92959c>[line:471] - INFO: temp save 350 batch train result, current acc1 0.5
2020-02-04 13:27:43,052 - <ipython-input-3-59b2da92959c>[line:452] - INFO: Pass 0, trainbatch 360, loss 1.1435649394989014, acc1 0.375, time 0.37 sec
2020-02-04 13:27:44,882 - <ipython-input-3-59b2da92959c>[line:456] - INFO: current acc1 1.0 meets good 0.92, successive count 1
2020-02-04 13:27:52,975 - <ipython-input-3-59b2da92959c>[line:477] - INFO: training till last epcho, end training In[4]
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import numpy as np
import random
import time
import codecs
import sys
import functools
import math
import paddle
import paddle.fluid as fluid
from paddle.fluid import core
from paddle.fluid.param_attr import ParamAttr
from PIL import Image, ImageEnhance
target_size = [3, 512, 512]
mean_rgb = [127.5, 127.5, 127.5]
data_dir = "data/data2815"
eval_file = "eval.txt"
use_gpu = True
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
save_freeze_dir = "./freeze-model"
[inference_program, feed_target_names, fetch_targets] = fluid.io.load_inference_model(dirname=save_freeze_dir, executor=exe)
# print(fetch_targets)
def crop_image(img, target_size):
width, height = img.size
p = min(target_size[2] / width, target_size[1] / height)
resized_h = int(height * p)
resized_w = int(width * p)
img = img.resize((resized_w, resized_h), Image.BILINEAR)
w_start = (resized_w - target_size[2]) / 2
h_start = (resized_h - target_size[1]) / 2
w_end = w_start + target_size[2]
h_end = h_start + target_size[1]
img = img.crop((w_start, h_start, w_end, h_end))
return img
def resize_img(img, target_size):
ret = img.resize((target_size[1], target_size[2]), Image.BILINEAR)
return ret
def read_image(img_path):
img = Image.open(img_path)
if img.mode != 'RGB':
img = img.convert('RGB')
# img = crop_image(img, target_size)
img = resize_img(img, target_size)
img = np.array(img).astype('float32')
img -= mean_rgb
img = img.transpose((2, 0, 1)) # HWC to CHW
img *= 0.007843
img = img[np.newaxis,:]
return img
def infer(image_path):
tensor_img = read_image(image_path)
label = exe.run(inference_program, feed={feed_target_names[0]: tensor_img}, fetch_list=fetch_targets)
return np.argmax(label)
def eval_all():
eval_file_path = os.path.join(data_dir, eval_file)
total_count = 0
right_count = 0
with codecs.open(eval_file_path, encoding='utf-8') as flist:
lines = [line.strip() for line in flist]
t1 = time.time()
for line in lines:
total_count += 1
parts = line.strip().split()
result = infer(parts[0])
# print("infer result:{0} answer:{1}".format(result, parts[1]))
if str(result) == parts[1]:
right_count += 1
period = time.time() - t1
print("total eval count:{0} cost time:{1} predict accuracy:{2}".format(total_count, "%2.2f sec" % period, right_count / total_count))
if __name__ == '__main__':
eval_all()total eval count:738 cost time:92.05 sec predict accuracy:0.6680216802168022
In[ ]
!tar -cf densenet.tar ./freeze-model点击链接，使用AI Studio一键上手实践项目吧：https://aistudio.baidu.com/aistudio/projectdetail/205040
下载安装命令
## CPU版本安装命令
pip install -f https://paddlepaddle.org.cn/pip/oschina/cpu paddlepaddle
## GPU版本安装命令
pip install -f https://paddlepaddle.org.cn/pip/oschina/gpu paddlepaddle-gpu>> 访问 PaddlePaddle 官网，了解更多相关内容。