-
Notifications
You must be signed in to change notification settings - Fork 518
/
CustomVisionQuickstart.py
170 lines (143 loc) · 7.72 KB
/
CustomVisionQuickstart.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
# <snippet_imports>
from azure.cognitiveservices.vision.customvision.training import CustomVisionTrainingClient
from azure.cognitiveservices.vision.customvision.prediction import CustomVisionPredictionClient
from azure.cognitiveservices.vision.customvision.training.models import ImageFileCreateBatch, ImageFileCreateEntry, Region
from msrest.authentication import ApiKeyCredentials
import os, time, uuid
# </snippet_imports>
'''
Prerequisites:
1. Install the Custom Vision SDK. Run:
pip install --upgrade azure-cognitiveservices-vision-customvision
2. Create an "Images" folder in your working directory.
3. Download the images used by this sample from:
https://github.com/Azure-Samples/cognitive-services-sample-data-files/tree/master/CustomVision/ObjectDetection/Images
This sample looks for images in the following paths:
<your working directory>/Images/fork
<your working directory>/Images/scissors
<your working directory>/Images/test
'''
# <snippet_creds>
# Replace with valid values
ENDPOINT = os.environ["VISION_TRAINING_ENDPOINT"]
training_key = os.environ["VISION_TRAINING_KEY"]
prediction_key = os.environ["VISION_PREDICTION_KEY"]
prediction_resource_id = os.environ["VISION_PREDICTION_RESOURCE_ID"]
# </snippet_creds>
# <snippet_auth>
credentials = ApiKeyCredentials(in_headers={"Training-key": training_key})
trainer = CustomVisionTrainingClient(ENDPOINT, credentials)
prediction_credentials = ApiKeyCredentials(in_headers={"Prediction-key": prediction_key})
predictor = CustomVisionPredictionClient(ENDPOINT, prediction_credentials)
# </snippet_auth>
# <snippet_create>
publish_iteration_name = "detectModel"
# Find the object detection domain
obj_detection_domain = next(domain for domain in trainer.get_domains() if domain.type == "ObjectDetection" and domain.name == "General")
# Create a new project
print ("Creating project...")
# Use uuid to avoid project name collisions.
project = trainer.create_project(str(uuid.uuid4()), domain_id=obj_detection_domain.id)
# </snippet_create>
# <snippet_tags>
# Make two tags in the new project
fork_tag = trainer.create_tag(project.id, "fork")
scissors_tag = trainer.create_tag(project.id, "scissors")
# </snippet_tags>
# <snippet_tagging>
fork_image_regions = {
"fork_1": [ 0.145833328, 0.3509314, 0.5894608, 0.238562092 ],
"fork_2": [ 0.294117659, 0.216944471, 0.534313738, 0.5980392 ],
"fork_3": [ 0.09191177, 0.0682516545, 0.757352948, 0.6143791 ],
"fork_4": [ 0.254901975, 0.185898721, 0.5232843, 0.594771266 ],
"fork_5": [ 0.2365196, 0.128709182, 0.5845588, 0.71405226 ],
"fork_6": [ 0.115196079, 0.133611143, 0.676470637, 0.6993464 ],
"fork_7": [ 0.164215669, 0.31008172, 0.767156839, 0.410130739 ],
"fork_8": [ 0.118872553, 0.318251669, 0.817401946, 0.225490168 ],
"fork_9": [ 0.18259804, 0.2136765, 0.6335784, 0.643790841 ],
"fork_10": [ 0.05269608, 0.282303959, 0.8088235, 0.452614367 ],
"fork_11": [ 0.05759804, 0.0894935, 0.9007353, 0.3251634 ],
"fork_12": [ 0.3345588, 0.07315363, 0.375, 0.9150327 ],
"fork_13": [ 0.269607842, 0.194068655, 0.4093137, 0.6732026 ],
"fork_14": [ 0.143382356, 0.218578458, 0.7977941, 0.295751631 ],
"fork_15": [ 0.19240196, 0.0633497, 0.5710784, 0.8398692 ],
"fork_16": [ 0.140931368, 0.480016381, 0.6838235, 0.240196079 ],
"fork_17": [ 0.305147052, 0.2512582, 0.4791667, 0.5408496 ],
"fork_18": [ 0.234068632, 0.445702642, 0.6127451, 0.344771236 ],
"fork_19": [ 0.219362751, 0.141781077, 0.5919118, 0.6683006 ],
"fork_20": [ 0.180147052, 0.239820287, 0.6887255, 0.235294119 ]
}
scissors_image_regions = {
"scissors_1": [ 0.4007353, 0.194068655, 0.259803921, 0.6617647 ],
"scissors_2": [ 0.426470578, 0.185898721, 0.172794119, 0.5539216 ],
"scissors_3": [ 0.289215684, 0.259428144, 0.403186262, 0.421568632 ],
"scissors_4": [ 0.343137264, 0.105833367, 0.332107842, 0.8055556 ],
"scissors_5": [ 0.3125, 0.09766343, 0.435049027, 0.71405226 ],
"scissors_6": [ 0.379901975, 0.24308826, 0.32107842, 0.5718954 ],
"scissors_7": [ 0.341911763, 0.20714055, 0.3137255, 0.6356209 ],
"scissors_8": [ 0.231617644, 0.08459154, 0.504901946, 0.8480392 ],
"scissors_9": [ 0.170343131, 0.332957536, 0.767156839, 0.403594762 ],
"scissors_10": [ 0.204656869, 0.120539248, 0.5245098, 0.743464053 ],
"scissors_11": [ 0.05514706, 0.159754932, 0.799019635, 0.730392158 ],
"scissors_12": [ 0.265931368, 0.169558853, 0.5061275, 0.606209159 ],
"scissors_13": [ 0.241421565, 0.184264734, 0.448529422, 0.6830065 ],
"scissors_14": [ 0.05759804, 0.05027781, 0.75, 0.882352948 ],
"scissors_15": [ 0.191176474, 0.169558853, 0.6936275, 0.6748366 ],
"scissors_16": [ 0.1004902, 0.279036, 0.6911765, 0.477124184 ],
"scissors_17": [ 0.2720588, 0.131977156, 0.4987745, 0.6911765 ],
"scissors_18": [ 0.180147052, 0.112369314, 0.6262255, 0.6666667 ],
"scissors_19": [ 0.333333343, 0.0274019931, 0.443627447, 0.852941155 ],
"scissors_20": [ 0.158088237, 0.04047389, 0.6691176, 0.843137264 ]
}
# </snippet_tagging>
# <snippet_upload>
base_image_location = os.path.join (os.path.dirname(__file__), "Images")
# Go through the data table above and create the images
print ("Adding images...")
tagged_images_with_regions = []
for file_name in fork_image_regions.keys():
x,y,w,h = fork_image_regions[file_name]
regions = [ Region(tag_id=fork_tag.id, left=x,top=y,width=w,height=h) ]
with open(os.path.join (base_image_location, "fork", file_name + ".jpg"), mode="rb") as image_contents:
tagged_images_with_regions.append(ImageFileCreateEntry(name=file_name, contents=image_contents.read(), regions=regions))
for file_name in scissors_image_regions.keys():
x,y,w,h = scissors_image_regions[file_name]
regions = [ Region(tag_id=scissors_tag.id, left=x,top=y,width=w,height=h) ]
with open(os.path.join (base_image_location, "scissors", file_name + ".jpg"), mode="rb") as image_contents:
tagged_images_with_regions.append(ImageFileCreateEntry(name=file_name, contents=image_contents.read(), regions=regions))
upload_result = trainer.create_images_from_files(project.id, ImageFileCreateBatch(images=tagged_images_with_regions))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
exit(-1)
# </snippet_upload>
# <snippet_train>
print ("Training...")
iteration = trainer.train_project(project.id)
while (iteration.status != "Completed"):
iteration = trainer.get_iteration(project.id, iteration.id)
print ("Training status: " + iteration.status)
time.sleep(1)
# </snippet_train>
# <snippet_publish>
# The iteration is now trained. Publish it to the project endpoint
trainer.publish_iteration(project.id, iteration.id, publish_iteration_name, prediction_resource_id)
print ("Done!")
# </snippet_publish>
# <snippet_test>
# Now there is a trained endpoint that can be used to make a prediction
# Open the sample image and get back the prediction results.
with open(os.path.join (base_image_location, "test", "test_image.jpg"), mode="rb") as test_data:
results = predictor.detect_image(project.id, publish_iteration_name, test_data)
# Display the results.
for prediction in results.predictions:
print("\t" + prediction.tag_name + ": {0:.2f}% bbox.left = {1:.2f}, bbox.top = {2:.2f}, bbox.width = {3:.2f}, bbox.height = {4:.2f}".format(prediction.probability * 100, prediction.bounding_box.left, prediction.bounding_box.top, prediction.bounding_box.width, prediction.bounding_box.height))
# </snippet_test>
# <snippet_delete>
# You cannot delete a project with published iterations, so you must first unpublish them.
print ("Unpublishing project...")
trainer.unpublish_iteration(project.id, iteration.id)
print ("Deleting project...")
trainer.delete_project(project.id)
# </snippet_delete>