Skip to content

M
models

PaddlePaddle / models
大约 1 年 前同步成功

通知 222
Star 6828
Fork 2962
M
models
提交 0116bc8d 编写于 作者: W wwhu
浏览文件
操作

add infer.py and flower dataset

上级 d7d1ae5a
隐藏空白更改
内联 并排
Showing with 176 addition and 42 deletion
image_classification/README.md
浏览文件 @ 0116bc8d
......@@ -3,20 +3,6 @@
这里将介绍如何在PaddlePaddle下使用AlexNet、VGG、GoogLeNet和ResNet模型进行图像分类。图像分类问题的描述和这四种模型的介绍可以参考[PaddlePaddle book](https://github.com/PaddlePaddle/book/tree/develop/03.image_classification)。
## 数据格式
reader.py定义了数据格式，它读取一个图像列表文件，并从中解析出图像路径和类别标签。
图像列表文件是一个文本文件，其中每一行由一个图像路径和类别标签构成，二者以跳格符（Tab）隔开。类别标签用整数表示，其最小值为0。下面给出一个图像列表文件的片段示例：
```
dataset_100/train_images/n03982430_23191.jpeg 1
dataset_100/train_images/n04461696_23653.jpeg 7
dataset_100/train_images/n02441942_3170.jpeg 8
dataset_100/train_images/n03733281_31716.jpeg 2
dataset_100/train_images/n03424325_240.jpeg 0
dataset_100/train_images/n02643566_75.jpeg 8
```
## 训练模型
### 初始化
......@@ -25,14 +11,14 @@ dataset_100/train_images/n02643566_75.jpeg 8
```python
import gzip
import paddle.v2.dataset.flowers as flowers
import paddle.v2 as paddle
import reader
import vgg
import resnet
import alexnet
import googlenet
import argparse
import os
# PaddlePaddle init
paddle.init(use_gpu=False, trainer_count=1)
......@@ -44,7 +30,7 @@ paddle.init(use_gpu=False, trainer_count=1)
```python
DATA_DIM = 3 * 224 * 224
CLASS_DIM = 100
CLASS_DIM = 102
BATCH_SIZE = 128
image = paddle.layer.data(
......@@ -128,9 +114,35 @@ optimizer = paddle.optimizer.Momentum(
$$ lr = lr_{0} * a^ {\lfloor \frac{n}{ b}\rfloor} $$
### 定义数据读取方法和事件处理程序
### 定义数据读取
首先以[花卉数据](http://www.robots.ox.ac.uk/~vgg/data/flowers/102/index.html)为例说明如何定义输入。下面的代码定义了花卉数据训练集和验证集的输入：
```python
train_reader = paddle.batch(
paddle.reader.shuffle(
flowers.train(),
buf_size=1000),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
flowers.valid(),
batch_size=BATCH_SIZE)
```
若需要使用其他数据，则需要先建立图像列表文件。`reader.py`定义了这种文件的读取方式，它从图像列表文件中解析出图像路径和类别标签。
图像列表文件是一个文本文件，其中每一行由一个图像路径和类别标签构成，二者以跳格符（Tab）隔开。类别标签用整数表示，其最小值为0。下面给出一个图像列表文件的片段示例：
读取数据时需要分别指定训练集和验证集的图像列表文件，这里假设这两个文件分别为`train.list`和`val.list`。
```
dataset_100/train_images/n03982430_23191.jpeg 1
dataset_100/train_images/n04461696_23653.jpeg 7
dataset_100/train_images/n02441942_3170.jpeg 8
dataset_100/train_images/n03733281_31716.jpeg 2
dataset_100/train_images/n03424325_240.jpeg 0
dataset_100/train_images/n02643566_75.jpeg 8
```
训练时需要分别指定训练集和验证集的图像列表文件。这里假设这两个文件分别为`train.list`和`val.list`，数据读取方式如下：
```python
train_reader = paddle.batch(
......@@ -141,7 +153,10 @@ train_reader = paddle.batch(
test_reader = paddle.batch(
reader.train_reader('val.list'),
batch_size=BATCH_SIZE)
```
### 定义事件处理程序
```python
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
......@@ -185,3 +200,38 @@ trainer = paddle.trainer.SGD(
trainer.train(
reader=train_reader, num_passes=200, event_handler=event_handler)
```
## 应用模型
模型训练好后，可以使用下面的代码预测给定图片的类别。
```python
# load parameters
with gzip.open('params_pass_10.tar.gz', 'r') as f:
parameters = paddle.parameters.Parameters.from_tar(f)
def load_image(file):
im = Image.open(file)
im = im.resize((224, 224), Image.ANTIALIAS)
im = np.array(im).astype(np.float32)
# The storage order of the loaded image is W(widht),
# H(height), C(channel). PaddlePaddle requires
# the CHW order, so transpose them.
im = im.transpose((2, 0, 1)) # CHW
# In the training phase, the channel order of CIFAR
# image is B(Blue), G(green), R(Red). But PIL open
# image in RGB mode. It must swap the channel order.
im = im[(2, 1, 0), :, :] # BGR
im = im.flatten()
im = im / 255.0
return im
file_list = [line.strip() for line in open(image_list_file)]
test_data = [(load_image(image_file),) for image_file in file_list]
probs = paddle.infer(
output_layer=out, parameters=parameters, input=test_data)
lab = np.argsort(-probs)
for file_name, result in zip(file_list, lab):
print "Label of %s is: %d" % (file_name, result[0])
```
首先从文件中加载训练好的模型（代码里以第10轮迭代的结果为例），然后读取`image_list_file`中的图像。`image_list_file`是一个文本文件，每一行为一个图像路径。`load_image`是一个加载图像的函数。代码使用`paddle.infer`判断`image_list_file`中每个图像的类别，并进行输出。
image_classification/infer.py 0 → 100644
浏览文件 @ 0116bc8d
import gzip
import paddle.v2 as paddle
import reader
import vgg
import resnet
import alexnet
import googlenet
import argparse
import os
from PIL import Image
import numpy as np
WIDTH = 224
HEIGHT = 224
DATA_DIM = 3 * WIDTH * HEIGHT
CLASS_DIM = 102
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'data_list',
help='The path of data list file, which consists of one image path per line'
)
parser.add_argument(
'model',
help='The model for image classification',
choices=['alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet', 'googlenet'])
parser.add_argument(
'params_path', help='The file which stores the parameters')
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
if args.model == 'alexnet':
out = alexnet.alexnet(image, class_dim=CLASS_DIM)
elif args.model == 'vgg13':
out = vgg.vgg13(image, class_dim=CLASS_DIM)
elif args.model == 'vgg16':
out = vgg.vgg16(image, class_dim=CLASS_DIM)
elif args.model == 'vgg19':
out = vgg.vgg19(image, class_dim=CLASS_DIM)
elif args.model == 'resnet':
out = resnet.resnet_imagenet(image, class_dim=CLASS_DIM)
elif args.model == 'googlenet':
out, _, _ = googlenet.googlenet(image, class_dim=CLASS_DIM)
# load parameters
with gzip.open(args.params_path, 'r') as f:
parameters = paddle.parameters.Parameters.from_tar(f)
def load_image(file):
im = Image.open(file)
im = im.resize((WIDTH, HEIGHT), Image.ANTIALIAS)
im = np.array(im).astype(np.float32)
# The storage order of the loaded image is W(widht),
# H(height), C(channel). PaddlePaddle requires
# the CHW order, so transpose them.
im = im.transpose((2, 0, 1)) # CHW
# In the training phase, the channel order of CIFAR
# image is B(Blue), G(green), R(Red). But PIL open
# image in RGB mode. It must swap the channel order.
im = im[(2, 1, 0), :, :] # BGR
im = im.flatten()
im = im / 255.0
return im
file_list = [line.strip() for line in open(args.data_list)]
test_data = [(load_image(image_file), ) for image_file in file_list]
probs = paddle.infer(
output_layer=out, parameters=parameters, input=test_data)
lab = np.argsort(-probs)
for file_name, result in zip(file_list, lab):
print "Label of %s is: %d" % (file_name, result[0])
if __name__ == '__main__':
main()
image_classification/resnet.py
浏览文件 @ 0116bc8d
......@@ -22,36 +22,36 @@ def conv_bn_layer(input,
return paddle.layer.batch_norm(input=tmp, act=active_type)
def shortcut(input, n_out, stride, b_projection):
if b_projection:
return conv_bn_layer(input, n_out, 1, stride, 0,
def shortcut(input, ch_in, ch_out, stride):
if ch_in != ch_out:
return conv_bn_layer(input, ch_out, 1, stride, 0,
paddle.activation.Linear())
else:
return input
def basicblock(input, ch_out, stride, b_projection):
def basicblock(input, ch_in, ch_out, stride):
short = shortcut(input, ch_in, ch_out, stride)
conv1 = conv_bn_layer(input, ch_out, 3, stride, 1)
conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1, paddle.activation.Linear())
short = shortcut(input, ch_out, stride, b_projection)
return paddle.layer.addto(
input=[conv2, short], act=paddle.activation.Relu())
input=[short, conv2], act=paddle.activation.Relu())
def bottleneck(input, ch_out, stride, b_projection):
def bottleneck(input, ch_in, ch_out, stride):
short = shortcut(input, ch_in, ch_out * 4, stride)
conv1 = conv_bn_layer(input, ch_out, 1, stride, 0)
conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1)
conv3 = conv_bn_layer(conv2, ch_out * 4, 1, 1, 0,
paddle.activation.Linear())
short = shortcut(input, ch_out * 4, stride, b_projection)
return paddle.layer.addto(
input=[conv3, short], act=paddle.activation.Relu())
input=[short, conv3], act=paddle.activation.Relu())
def layer_warp(block_func, input, features, count, stride):
conv = block_func(input, features, stride, True)
def layer_warp(block_func, input, ch_in, ch_out, count, stride):
conv = block_func(input, ch_in, ch_out, stride)
for i in range(1, count):
conv = block_func(conv, features, 1, False)
conv = block_func(conv, ch_in, ch_out, 1)
return conv
......@@ -67,10 +67,10 @@ def resnet_imagenet(input, depth=50, class_dim=100):
conv1 = conv_bn_layer(
input, ch_in=3, ch_out=64, filter_size=7, stride=2, padding=3)
pool1 = paddle.layer.img_pool(input=conv1, pool_size=3, stride=2)
res1 = layer_warp(block_func, pool1, 64, stages[0], 1)
res2 = layer_warp(block_func, res1, 128, stages[1], 2)
res3 = layer_warp(block_func, res2, 256, stages[2], 2)
res4 = layer_warp(block_func, res3, 512, stages[3], 2)
res1 = layer_warp(block_func, pool1, 64, 64, stages[0], 1)
res2 = layer_warp(block_func, res1, 64, 128, stages[1], 2)
res3 = layer_warp(block_func, res2, 128, 256, stages[2], 2)
res4 = layer_warp(block_func, res3, 256, 512, stages[3], 2)
pool2 = paddle.layer.img_pool(
input=res4, pool_size=7, stride=1, pool_type=paddle.pooling.Avg())
out = paddle.layer.fc(
......
image_classification/train.py
浏览文件 @ 0116bc8d
import gzip
import paddle.v2.dataset.flowers as flowers
import paddle.v2 as paddle
import reader
import vgg
......@@ -6,19 +7,15 @@ import resnet
import alexnet
import googlenet
import argparse
import os
DATA_DIM = 3 * 224 * 224
CLASS_DIM = 100
CLASS_DIM = 102
BATCH_SIZE = 128
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'data_dir',
help='The data directory which contains train.list and val.list')
parser.add_argument(
'model',
help='The model for image classification',
......@@ -71,11 +68,15 @@ def main():
train_reader = paddle.batch(
paddle.reader.shuffle(
reader.test_reader(os.path.join(args.data_dir, 'train.list')),
flowers.train(),
# To use other data, replace the above line with:
# reader.test_reader('train.list'),
buf_size=1000),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
reader.train_reader(os.path.join(args.data_dir, 'val.list')),
flowers.valid(),
# To use other data, replace the above line with:
# reader.train_reader('val.list'),
batch_size=BATCH_SIZE)
# End batch and end pass event handler
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或