Commit 02d8d3cc authored by sleepless-se's avatar sleepless-se
Browse files

Initial commit

parents
Pipeline #67671167 passed with stage
in 11 minutes and 45 seconds
# This file is a template, and might need editing before it works on your project.
# Official docker image.
image: docker:latest
services:
- docker:dind
before_script:
- docker login -u "$CI_REGISTRY_USER" -p "$CI_REGISTRY_PASSWORD" $CI_REGISTRY
build-master:
stage: build
script:
- docker build --pull -t "$CI_REGISTRY_IMAGE" .
- docker push "$CI_REGISTRY_IMAGE"
only:
- master
build:
stage: build
script:
- docker build --pull -t "$CI_REGISTRY_IMAGE:$CI_COMMIT_REF_SLUG" .
- docker push "$CI_REGISTRY_IMAGE:$CI_COMMIT_REF_SLUG"
except:
- master
# FROM tensorflow/tensorflow:latest-gpu-py3
FROM gpueater/ubuntu16-rocm-1.9.211-tensorflow-1.11.0
MAINTAINER sleepless-se "sleepless.se@gmail.com"
COPY . /app
RUN apt update && apt install -y git wget curl tar zip unzip python-pil python-lxml vim nginx python3-pip zlib1g-dev libssl-dev libsm6 libxext6 libxrender-dev
RUN wget https://www.python.org/ftp/python/3.7.1/Python-3.7.1.tgz && \
tar -xzf Python-3.7.1.tgz && \
cd Python-3.7.1 && \
./configure && \
make && \
make install
RUN pip3 install uwsgi flask supervisor && pip3 install -r /app/requirements.txt
RUN pip3 install https://github.com/OlafenwaMoses/ImageAI/releases/download/2.0.2/imageai-2.0.2-py3-none-any.whl
WORKDIR /app
RUN cp etc/nginx.conf /etc/nginx/nginx.conf
RUN cp etc/uwsgi.ini /etc/uwsgi.ini
RUN cp etc/supervisord.conf /etc/supervisord.conf
RUN wget https://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/yolo.h5
EXPOSE 80 5000
CMD ["/usr/local/bin/supervisord"]
\ No newline at end of file
MIT License
Copyright (c) 2019 sleepless-se
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
# ImageAI Object Detection API
## Setup
`docker run -p 80:80 registry.gitlab.com/sleepless-se/imageai_object_detection_api:latest`
## Test
**Access**
http://localhost
You can see `Welcome to Object detection!`
**Object ditection**
Send your image to the API. It's return the result of object detection by YOLOv3.
`curl -X POST -F image=@path/to/image.jpg http://localhost/predict`
Please replace to your image path `path/to/image.jpg`
## Develop
You can edit ImageAI API.
1. Clone repository `git clone git@gitlab.com:sleepless-se/imageai_object_detection_api.git`
1. Edit `imageai_object_detection_api/api.py` as you want.
Here is [ImageAI Document](https://imageai.readthedocs.io/en/latest/)
## Build Push
If you are fork on GitLab it's automatically build and push on the GitLab Container Registry.
#!/usr/bin/env python
# coding: utf-8
# # Object Detection Demo
# Welcome to the object detection inference walkthrough! This notebook will walk you step by step through the process of using a pre-trained model to detect objects in an image. Make sure to follow the [installation instructions](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md) before you start.
# # Imports
# In[12]:
import numpy as np
import os
import tensorflow as tf
from PIL import Image
import time
from flask import Flask
from flask import request
from flask import jsonify
import json
from yolo import YOLO
EXCUTION_PATH = '/app'
yolo =YOLO()
graph = tf.get_default_graph()
classes = []
with open('model_data/voc_classes.txt') as f:
classes = f.read().split()
class MyEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, np.integer):
return int(obj)
elif isinstance(obj, np.floating):
return float(obj)
elif isinstance(obj, np.ndarray):
return obj.tolist()
else:
return super(MyEncoder, self).default(obj)
def image_to_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
def predict_image(image):
image = Image.open(image)
image = image.convert("RGB")
with graph.as_default():
result = yolo.detect_image(image)
import cv2
cv2.imwrite("out.jpg", np.asarray(result['image'])[..., ::-1])
return result
def return_format(data):
new_data = {}
boxs = []
names = []
for box in data['box_points']:
boxs.append([box[1],box[0],box[3],box[2]])
for name in data['name']:
names.append(classes[name])
new_data['box_points'] = boxs
new_data['percentage_probability'] = data['percentage_probability'] * 100
new_data['name'] = names
return new_data
app = Flask(__name__)
@app.route("/")
def home():
return "Welcome to keras-yolo3 Object Detection API!"
@app.route("/predict", methods=['POST'])
def predict():
if request.method == 'POST':
data = request.files
try:
data = predict_image(data['image'])
print(data)
data = return_format(data)
data = json.dumps(data, cls=MyEncoder)
return jsonify(data)
except Exception as e:
print(e)
return "ERROR:{}".format(e)
else:
return "no post"
if __name__ == '__main__':
app.run(host="0.0.0.0", port=5000, debug=True)
worker_processes 1;
error_log /var/log/nginx/error.log warn;
pid /var/run/nginx.pid;
events {
worker_connections 1024;
}
http {
include /etc/nginx/mime.types;
default_type application/octet-stream;
log_format main '$remote_addr - $remote_user [$time_local] "$request" '
'$status $body_bytes_sent "$http_referer" '
'"$http_user_agent" "$http_x_forwarded_for"';
access_log /var/log/nginx/access.log main;
sendfile on;
#tcp_nopush on;
keepalive_timeout 65;
#gzip on;
upstream uwsgi {
server localhost:3031;
}
server {
listen 80;
charset utf-8;
location / {
include uwsgi_params;
uwsgi_pass 127.0.0.1:3031;
}
location /static {
alias /static;
}
location /media {
alias /media;
}
}
}
\ No newline at end of file
[supervisord]
nodaemon=true
[program:uwsgi]
command=/usr/local/bin/uwsgi --ini /etc/uwsgi.ini --die-on-term
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:nginx]
command=/usr/sbin/nginx -g "daemon off;"
stdout_logfile=/dev/stdout
stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
\ No newline at end of file
[uwsgi]
wsgi-file=/app/api.py
socket=127.0.0.1:3031
callable = app
processes = 4
threads = 2
\ No newline at end of file
Copyright (c) 2014, Mozilla Foundation https://mozilla.org/ with Reserved Font Name Fira Mono.
Copyright (c) 2014, Telefonica S.A.
This Font Software is licensed under the SIL Open Font License, Version 1.1.
This license is copied below, and is also available with a FAQ at: http://scripts.sil.org/OFL
-----------------------------------------------------------
SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
-----------------------------------------------------------
PREAMBLE
The goals of the Open Font License (OFL) are to stimulate worldwide development of collaborative font projects, to support the font creation efforts of academic and linguistic communities, and to provide a free and open framework in which fonts may be shared and improved in partnership with others.
The OFL allows the licensed fonts to be used, studied, modified and redistributed freely as long as they are not sold by themselves. The fonts, including any derivative works, can be bundled, embedded, redistributed and/or sold with any software provided that any reserved names are not used by derivative works. The fonts and derivatives, however, cannot be released under any other type of license. The requirement for fonts to remain under this license does not apply to any document created using the fonts or their derivatives.
DEFINITIONS
"Font Software" refers to the set of files released by the Copyright Holder(s) under this license and clearly marked as such. This may include source files, build scripts and documentation.
"Reserved Font Name" refers to any names specified as such after the copyright statement(s).
"Original Version" refers to the collection of Font Software components as distributed by the Copyright Holder(s).
"Modified Version" refers to any derivative made by adding to, deleting, or substituting -- in part or in whole -- any of the components of the Original Version, by changing formats or by porting the Font Software to a new environment.
"Author" refers to any designer, engineer, programmer, technical writer or other person who contributed to the Font Software.
PERMISSION & CONDITIONS
Permission is hereby granted, free of charge, to any person obtaining a copy of the Font Software, to use, study, copy, merge, embed, modify, redistribute, and sell modified and unmodified copies of the Font Software, subject to the following conditions:
1) Neither the Font Software nor any of its individual components, in Original or Modified Versions, may be sold by itself.
2) Original or Modified Versions of the Font Software may be bundled, redistributed and/or sold with any software, provided that each copy contains the above copyright notice and this license. These can be included either as stand-alone text files, human-readable headers or in the appropriate machine-readable metadata fields within text or binary files as long as those fields can be easily viewed by the user.
3) No Modified Version of the Font Software may use the Reserved Font Name(s) unless explicit written permission is granted by the corresponding Copyright Holder. This restriction only applies to the primary font name as presented to the users.
4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font Software shall not be used to promote, endorse or advertise any Modified Version, except to acknowledge the contribution(s) of the Copyright Holder(s) and the Author(s) or with their explicit written permission.
5) The Font Software, modified or unmodified, in part or in whole, must be distributed entirely under this license, and must not be distributed under any other license. The requirement for fonts to remain under this license does not apply to any document created using the Font Software.
TERMINATION
This license becomes null and void if any of the above conditions are not met.
DISCLAIMER
THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM OTHER DEALINGS IN THE FONT SOFTWARE.
\ No newline at end of file
absl-py==0.7.1
astor==0.8.0
bleach==1.5.0
Cython==0.29.7
contextlib2==0.5.5
cycler==0.10.0
Flask==1.0.2
gast==0.2.2
grpcio==1.21.1
gevent
h5py==2.9.0
html5lib==0.9999999
jupyter==1.0.0
jupyter-client==5.2.4
jupyter-console==6.0.0
jupyter-core==4.4.0
Keras==2.1.5
kiwisolver==1.1.0
lxml==4.3.3
Markdown==3.1.1
matplotlib==3.0.3
numpy==1.16.4
opencv-python
Pillow==6.0.0
protobuf==3.8.0
pyparsing==2.4.0
python-dateutil==2.8.0
PyYAML==5.1.1
requests
uwsgi
scipy==1.3.0
six==1.12.0
tensorboard==1.6.0
tensorflow==1.13.1
termcolor==1.1.0
Werkzeug==0.15.4
# -*- coding: utf-8 -*-
"""
Class definition of YOLO_v3 style detection model on image and video
"""
import colorsys
import os
from timeit import default_timer as timer
import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw
from yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
from yolo3.utils import letterbox_image
import os
from keras.utils import multi_gpu_model
class YOLO(object):
_defaults = {
# "model_path": 'model_data/yolo.h5',
"model_path": 'model_data/yolo.h5',
"anchors_path": 'model_data/yolo_anchors.txt',
"classes_path": 'model_data/voc_classes.txt',
"score" : 0.3,
"iou" : 0.45,
"model_image_size" : (320, 320),
"gpu_num" : 1,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
def __init__(self, **kwargs):
self.__dict__.update(self._defaults) # set up default values
self.__dict__.update(kwargs) # and update with user overrides
self.class_names = self._get_class()
self.anchors = self._get_anchors()
self.sess = K.get_session()
self.boxes, self.scores, self.classes = self.generate()
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def _get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
# Load model, or construct model and load weights.
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
is_tiny_version = num_anchors==6 # default setting
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \
if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# Generate colors for drawing bounding boxes.
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
np.random.seed(10101) # Fixed seed for consistent colors across runs.
np.random.shuffle(self.colors) # Shuffle colors to decorrelate adjacent classes.
np.random.seed(None) # Reset seed to default.
# Generate output tensor targets for filtered bounding boxes.
self.input_image_shape = K.placeholder(shape=(2, ))
if self.gpu_num>=2:
self.yolo_model = multi_gpu_model(self.yolo_model, gpus=self.gpu_num)
boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
len(self.class_names), self.input_image_shape,
score_threshold=self.score, iou_threshold=self.iou)
return boxes, scores, classes
def detect_image(self, image):
start = timer()
if self.model_image_size != (None, None):
assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
boxed_image = letterbox_image(image, tuple(reversed(self.model_image_size)))
else:
new_image_size = (image.width - (image.width % 32),
image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
print(image_data.shape)
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo_model.input: image_data,
self.input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0
})
result = {}
result['name'] = out_classes
result['percentage_probability'] = out_scores
result['box_points'] = out_boxes
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
thickness = (image.size[0] + image.size[1]) // 300
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
top, left, bottom, right = box
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
print(label, (left, top), (right, bottom))
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
# My kingdom for a good redistributable image drawing library.
for i in range(thickness):
draw.rectangle(
[left + i, top + i, right - i, bottom - i],
outline=self.colors[c])
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[c])
draw.text(text_origin, label, fill=(0, 0, 0), font=font)
del draw
end = timer()
print(end - start)
result['image'] = image
print(result)
return result
def close_session(self):
self.sess.close()
def detect_video(yolo, video_path, output_path=""):
import cv2
vid = cv2.VideoCapture(video_path)
if not vid.isOpened():
raise IOError("Couldn't open webcam or video")
video_FourCC = int(vid.get(cv2.CAP_PROP_FOURCC))
video_fps = vid.get(cv2.CAP_PROP_FPS)
video_size = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))
isOutput = True if output_path != "" else False
if isOutput:
print("!!! TYPE:", type(output_path), type(video_FourCC), type(video_fps), type(video_size))
out = cv2.VideoWriter(output_path, video_FourCC, video_fps, video_size)
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
image = Image.fromarray(frame)
image = yolo.detect_image(image)
result = np.asarray(image)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", result)
if isOutput:
out.write(result)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
yolo.close_session()
"""YOLO_v3 Model Defined in Keras."""