Skip to content

P
PaddleHub

PaddlePaddle / PaddleHub
大约 1 年 前同步成功

通知 282
Star 12117
Fork 2091
P
PaddleHub
未验证 提交 e081f3fb 编写于 作者: H haoyuying 提交者： GitHub
浏览文件
操作

update mobilenet_v3_large_imagenet_ssld

上级 c07d1ffe
展开全部 显示空白变更内容
内联 并排
Showing with 257 addition and 1852 deletion
hub_module/modules/image/classification/mobilenet_v3_large_imagenet_ssld/README.md 已删除 100644 → 0
浏览文件 @ c07d1ffe
```shell
$ hub install mobilenet_v3_large_imagenet_ssld==1.0.0
```
## 命令行预测
```
hub run mobilenet_v3_large_imagenet_ssld --input_path "/PATH/TO/IMAGE"
```
## API
```python
def get_expected_image_width()
```
返回预处理的图片宽度，也就是224。
```python
def get_expected_image_height()
```
返回预处理的图片高度，也就是224。
```python
def get_pretrained_images_mean()
```
返回预处理的图片均值，也就是 \[0.485, 0.456, 0.406\]。
```python
def get_pretrained_images_std()
```
返回预处理的图片标准差，也就是 \[0.229, 0.224, 0.225\]。
```python
def context(trainable=True, pretrained=True)
```
**参数**
* trainable (bool): 计算图的参数是否为可训练的；
* pretrained (bool): 是否加载默认的预训练模型。
**返回**
* inputs (dict): 计算图的输入，key 为 'image', value 为图片的张量；
* outputs (dict): 计算图的输出，key 为 'classification' 和 'feature_map'，其相应的值为：
* classification (paddle.fluid.framework.Variable): 分类结果，也就是全连接层的输出；
* feature\_map (paddle.fluid.framework.Variable): 特征匹配，全连接层前面的那个张量。
* context\_prog(fluid.Program): 计算图，用于迁移学习。
```python
def classification(images=None,
paths=None,
batch_size=1,
use_gpu=False,
top_k=1):
```
**参数**
* images (list\[numpy.ndarray\]): 图片数据，每一个图片数据的shape 均为 \[H, W, C\]，颜色空间为 BGR；
* paths (list\[str\]): 图片的路径；
* batch\_size (int): batch 的大小；
* use\_gpu (bool): 是否使用 GPU 来预测；
* top\_k (int): 返回预测结果的前 k 个。
**返回**
res (list\[dict\]): 分类结果，列表的每一个元素均为字典，其中 key 为识别动物的类别，value为置信度。
```python
def save_inference_model(dirname,
model_filename=None,
params_filename=None,
combined=True)
```
将模型保存到指定路径。
**参数**
* dirname: 存在模型的目录名称
* model_filename: 模型文件名称，默认为\_\_model\_\_
* params_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)
* combined: 是否将参数保存到统一的一个文件中
## 代码示例
```python
import paddlehub as hub
import cv2
classifier = hub.Module(name="mobilenet_v3_large_imagenet_ssld")
result = classifier.classification(images=[cv2.imread('/PATH/TO/IMAGE')])
# or
# result = classifier.classification(paths=['/PATH/TO/IMAGE'])
```
## 服务部署
PaddleHub Serving可以部署一个在线动物识别服务。
## 第一步：启动PaddleHub Serving
运行启动命令：
```shell
$ hub serving start -m mobilenet_v3_large_imagenet_ssld
```
这样就完成了一个在线动物识别服务化API的部署，默认端口号为8866。
**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
## 第二步：发送预测请求
配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
```python
import requests
import json
import cv2
import base64
def cv2_to_base64(image):
data = cv2.imencode('.jpg', image)[1]
return base64.b64encode(data.tostring()).decode('utf8')
# 发送HTTP请求
data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
headers = {"Content-type": "application/json"}
url = "http://127.0.0.1:8866/predict/mobilenet_v3_large_imagenet_ssld"
r = requests.post(url=url, headers=headers, data=json.dumps(data))
# 打印预测结果
print(r.json()["results"])
```
### 查看代码
[PaddleClas](https://github.com/PaddlePaddle/PaddleClas)
### 依赖
paddlepaddle >= 1.6.2
paddlehub >= 1.6.0
hub_module/modules/image/classification/mobilenet_v3_large_imagenet_ssld/data_feed.py 已删除 100644 → 0
浏览文件 @ c07d1ffe
# coding=utf-8
import os
import time
from collections import OrderedDict
import cv2
import numpy as np
from PIL import Image
__all__ = ['reader']
DATA_DIM = 224
img_mean = np.array([0.485, 0.456, 0.406]).reshape((3, 1, 1))
img_std = np.array([0.229, 0.224, 0.225]).reshape((3, 1, 1))
def resize_short(img, target_size):
percent = float(target_size) / min(img.size[0], img.size[1])
resized_width = int(round(img.size[0] * percent))
resized_height = int(round(img.size[1] * percent))
img = img.resize((resized_width, resized_height), Image.LANCZOS)
return img
def crop_image(img, target_size, center):
width, height = img.size
size = target_size
if center == True:
w_start = (width - size) / 2
h_start = (height - size) / 2
else:
w_start = np.random.randint(0, width - size + 1)
h_start = np.random.randint(0, height - size + 1)
w_end = w_start + size
h_end = h_start + size
img = img.crop((w_start, h_start, w_end, h_end))
return img
def process_image(img):
img = resize_short(img, target_size=256)
img = crop_image(img, target_size=DATA_DIM, center=True)
if img.mode != 'RGB':
img = img.convert('RGB')
img = np.array(img).astype('float32').transpose((2, 0, 1)) / 255
img -= img_mean
img /= img_std
return img
def reader(images=None, paths=None):
"""
Preprocess to yield image.
Args:
images (list[numpy.ndarray]): images data, shape of each is [H, W, C].
paths (list[str]): paths to images.
Yield:
each (collections.OrderedDict): info of original image, preprocessed image.
"""
component = list()
if paths:
for im_path in paths:
each = OrderedDict()
assert os.path.isfile(
im_path), "The {} isn't a valid file path.".format(im_path)
each['org_im_path'] = im_path
each['org_im'] = Image.open(im_path)
each['org_im_width'], each['org_im_height'] = each['org_im'].size
component.append(each)
if images is not None:
assert type(images), "images is a list."
for im in images:
each = OrderedDict()
each['org_im'] = Image.fromarray(im[:, :, ::-1])
each['org_im_path'] = 'ndarray_time={}'.format(
round(time.time(), 6) * 1e6)
each['org_im_width'], each['org_im_height'] = each['org_im'].size
component.append(each)
for element in component:
element['image'] = process_image(element['org_im'])
yield element
hub_module/modules/image/classification/mobilenet_v3_large_imagenet_ssld/mobilenet_v3.py 已删除 100644 → 0
浏览文件 @ c07d1ffe
# copyright (c) 2020 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 paddle.fluid as fluid
from paddle.fluid.initializer import MSRA
from paddle.fluid.param_attr import ParamAttr
__all__ = [
'MobileNetV3', 'MobileNetV3_small_x0_35', 'MobileNetV3_small_x0_5',
'MobileNetV3_small_x0_75', 'MobileNetV3_small_x1_0',
'MobileNetV3_small_x1_25', 'MobileNetV3_large_x0_35',
'MobileNetV3_large_x0_5', 'MobileNetV3_large_x0_75',
'MobileNetV3_large_x1_0', 'MobileNetV3_large_x1_25'
]
class MobileNetV3():
def __init__(self, scale=1.0, model_name='small'):
self.scale = scale
self.inplanes = 16
if model_name == "large":
self.cfg = [
# k, exp, c, se, nl, s,
[3, 16, 16, False, 'relu', 1],
[3, 64, 24, False, 'relu', 2],
[3, 72, 24, False, 'relu', 1],
[5, 72, 40, True, 'relu', 2],
[5, 120, 40, True, 'relu', 1],
[5, 120, 40, True, 'relu', 1],
[3, 240, 80, False, 'hard_swish', 2],
[3, 200, 80, False, 'hard_swish', 1],
[3, 184, 80, False, 'hard_swish', 1],
[3, 184, 80, False, 'hard_swish', 1],
[3, 480, 112, True, 'hard_swish', 1],
[3, 672, 112, True, 'hard_swish', 1],
[5, 672, 160, True, 'hard_swish', 2],
[5, 960, 160, True, 'hard_swish', 1],
[5, 960, 160, True, 'hard_swish', 1],
]
self.cls_ch_squeeze = 960
self.cls_ch_expand = 1280
elif model_name == "small":
self.cfg = [
# k, exp, c, se, nl, s,
[3, 16, 16, True, 'relu', 2],
[3, 72, 24, False, 'relu', 2],
[3, 88, 24, False, 'relu', 1],
[5, 96, 40, True, 'hard_swish', 2],
[5, 240, 40, True, 'hard_swish', 1],
[5, 240, 40, True, 'hard_swish', 1],
[5, 120, 48, True, 'hard_swish', 1],
[5, 144, 48, True, 'hard_swish', 1],
[5, 288, 96, True, 'hard_swish', 2],
[5, 576, 96, True, 'hard_swish', 1],
[5, 576, 96, True, 'hard_swish', 1],
]
self.cls_ch_squeeze = 576
self.cls_ch_expand = 1280
else:
raise NotImplementedError("mode[" + model_name +
"_model] is not implemented!")
def net(self, input, class_dim=1000):
scale = self.scale
inplanes = self.inplanes
cfg = self.cfg
cls_ch_squeeze = self.cls_ch_squeeze
cls_ch_expand = self.cls_ch_expand
#conv1
conv = self.conv_bn_layer(
input,
filter_size=3,
num_filters=self.make_divisible(inplanes * scale),
stride=2,
padding=1,
num_groups=1,
if_act=True,
act='hard_swish',
name='conv1')
i = 0
inplanes = self.make_divisible(inplanes * scale)
for layer_cfg in cfg:
conv = self.residual_unit(
input=conv,
num_in_filter=inplanes,
num_mid_filter=self.make_divisible(scale * layer_cfg[1]),
num_out_filter=self.make_divisible(scale * layer_cfg[2]),
act=layer_cfg[4],
stride=layer_cfg[5],
filter_size=layer_cfg[0],
use_se=layer_cfg[3],
name='conv' + str(i + 2))
inplanes = self.make_divisible(scale * layer_cfg[2])
i += 1
conv = self.conv_bn_layer(
input=conv,
filter_size=1,
num_filters=self.make_divisible(scale * cls_ch_squeeze),
stride=1,
padding=0,
num_groups=1,
if_act=True,
act='hard_swish',
name='conv_last')
conv = fluid.layers.pool2d(
input=conv, pool_type='avg', global_pooling=True, use_cudnn=False)
conv = fluid.layers.conv2d(
input=conv,
num_filters=cls_ch_expand,
filter_size=1,
stride=1,
padding=0,
act=None,
param_attr=ParamAttr(name='last_1x1_conv_weights'),
bias_attr=False)
conv = fluid.layers.hard_swish(conv)
drop = fluid.layers.dropout(x=conv, dropout_prob=0.2)
out = fluid.layers.fc(
input=drop,
size=class_dim,
param_attr=ParamAttr(name='fc_weights'),
bias_attr=ParamAttr(name='fc_offset'))
return out, drop
def conv_bn_layer(self,
input,
filter_size,
num_filters,
stride,
padding,
num_groups=1,
if_act=True,
act=None,
name=None,
use_cudnn=True,
res_last_bn_init=False):
conv = fluid.layers.conv2d(
input=input,
num_filters=num_filters,
filter_size=filter_size,
stride=stride,
padding=padding,
groups=num_groups,
act=None,
use_cudnn=use_cudnn,
param_attr=ParamAttr(name=name + '_weights'),
bias_attr=False)
bn_name = name + '_bn'
bn = fluid.layers.batch_norm(
input=conv,
param_attr=ParamAttr(
name=bn_name + "_scale",
regularizer=fluid.regularizer.L2DecayRegularizer(
regularization_coeff=0.0)),
bias_attr=ParamAttr(
name=bn_name + "_offset",
regularizer=fluid.regularizer.L2DecayRegularizer(
regularization_coeff=0.0)),
moving_mean_name=bn_name + '_mean',
moving_variance_name=bn_name + '_variance')
if if_act:
if act == 'relu':
bn = fluid.layers.relu(bn)
elif act == 'hard_swish':
bn = fluid.layers.hard_swish(bn)
return bn
def make_divisible(self, v, divisor=8, min_value=None):
if min_value is None:
min_value = divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
if new_v < 0.9 * v:
new_v += divisor
return new_v
def se_block(self, input, num_out_filter, ratio=4, name=None):
num_mid_filter = num_out_filter // ratio
pool = fluid.layers.pool2d(
input=input, pool_type='avg', global_pooling=True, use_cudnn=False)
conv1 = fluid.layers.conv2d(
input=pool,
filter_size=1,
num_filters=num_mid_filter,
act='relu',
param_attr=ParamAttr(name=name + '_1_weights'),
bias_attr=ParamAttr(name=name + '_1_offset'))
conv2 = fluid.layers.conv2d(
input=conv1,
filter_size=1,
num_filters=num_out_filter,
act='hard_sigmoid',
param_attr=ParamAttr(name=name + '_2_weights'),
bias_attr=ParamAttr(name=name + '_2_offset'))
scale = fluid.layers.elementwise_mul(x=input, y=conv2, axis=0)
return scale
def residual_unit(self,
input,
num_in_filter,
num_mid_filter,
num_out_filter,
stride,
filter_size,
act=None,
use_se=False,
name=None):
conv0 = self.conv_bn_layer(
input=input,
filter_size=1,
num_filters=num_mid_filter,
stride=1,
padding=0,
if_act=True,
act=act,
name=name + '_expand')
conv1 = self.conv_bn_layer(
input=conv0,
filter_size=filter_size,
num_filters=num_mid_filter,
stride=stride,
padding=int((filter_size - 1) // 2),
if_act=True,
act=act,
num_groups=num_mid_filter,
use_cudnn=False,
name=name + '_depthwise')
if use_se:
conv1 = self.se_block(
input=conv1, num_out_filter=num_mid_filter, name=name + '_se')
conv2 = self.conv_bn_layer(
input=conv1,
filter_size=1,
num_filters=num_out_filter,
stride=1,
padding=0,
if_act=False,
name=name + '_linear',
res_last_bn_init=True)
if num_in_filter != num_out_filter or stride != 1:
return conv2
else:
return fluid.layers.elementwise_add(x=input, y=conv2, act=None)
def MobileNetV3_small_x0_35():
model = MobileNetV3(model_name='small', scale=0.35)
return model
def MobileNetV3_small_x0_5():
model = MobileNetV3(model_name='small', scale=0.5)
return model
def MobileNetV3_small_x0_75():
model = MobileNetV3(model_name='small', scale=0.75)
return model
def MobileNetV3_small_x1_0():
model = MobileNetV3(model_name='small', scale=1.0)
return model
def MobileNetV3_small_x1_25():
model = MobileNetV3(model_name='small', scale=1.25)
return model
def MobileNetV3_large_x0_35():
model = MobileNetV3(model_name='large', scale=0.35)
return model
def MobileNetV3_large_x0_5():
model = MobileNetV3(model_name='large', scale=0.5)
return model
def MobileNetV3_large_x0_75():
model = MobileNetV3(model_name='large', scale=0.75)
return model
def MobileNetV3_large_x1_0():
model = MobileNetV3(model_name='large', scale=1.0)
return model
def MobileNetV3_large_x1_25():
model = MobileNetV3(model_name='large', scale=1.25)
return model
hub_module/modules/image/classification/mobilenet_v3_large_imagenet_ssld/processor.py 已删除 100644 → 0
浏览文件 @ c07d1ffe
# coding=utf-8
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import base64
import cv2
import os
import numpy as np
def base64_to_cv2(b64str):
data = base64.b64decode(b64str.encode('utf8'))
data = np.fromstring(data, np.uint8)
data = cv2.imdecode(data, cv2.IMREAD_COLOR)
return data
def softmax(x):
orig_shape = x.shape
if len(x.shape) > 1:
tmp = np.max(x, axis=1)
x -= tmp.reshape((x.shape[0], 1))
x = np.exp(x)
tmp = np.sum(x, axis=1)
x /= tmp.reshape((x.shape[0], 1))
else:
tmp = np.max(x)
x -= tmp
x = np.exp(x)
tmp = np.sum(x)
x /= tmp
return x
def postprocess(data_out, label_list, top_k):
"""
Postprocess output of network, one image at a time.
Args:
data_out (numpy.ndarray): output data of network.
label_list (list): list of label.
top_k (int): Return top k results.
"""
output = []
for result in data_out:
result_i = softmax(result)
output_i = {}
indexs = np.argsort(result_i)[::-1][0:top_k]
for index in indexs:
label = label_list[index].split(',')[0]
output_i[label] = float(result_i[index])
output.append(output_i)
return output
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