Skip to content

Commit e3b4e2f

Browse files
SivertHuseboSivertHusebo
committed
Removed dev file
1 parent 0f5e556 commit e3b4e2f

File tree

7 files changed

+2573
-0
lines changed

7 files changed

+2573
-0
lines changed

‎.dev_secret

Whitespace-only changes.

‎sam2/sam2.ipynb

+611
Large diffs are not rendered by default.

‎segment_geospatial/samgeo2.ipynb

+982
Large diffs are not rendered by default.

‎segment_geospatial/samgeo2_automatic.ipynb

+229
Large diffs are not rendered by default.

‎segment_geospatial/samgeo_automatic.ipynb

+276
Large diffs are not rendered by default.

‎vision_models/azure_ai_vision.ipynb

+232
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,232 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {},
6+
"source": [
7+
"Import libraries."
8+
]
9+
},
10+
{
11+
"cell_type": "code",
12+
"execution_count": null,
13+
"metadata": {},
14+
"outputs": [],
15+
"source": [
16+
"import os\n",
17+
"from azure.ai.vision.imageanalysis import ImageAnalysisClient\n",
18+
"from azure.ai.vision.imageanalysis.models import VisualFeatures\n",
19+
"from azure.core.credentials import AzureKeyCredential\n",
20+
"from pdf2image import convert_from_path"
21+
]
22+
},
23+
{
24+
"cell_type": "markdown",
25+
"metadata": {},
26+
"source": [
27+
"Helper function for turning pdfs to jpgs."
28+
]
29+
},
30+
{
31+
"cell_type": "code",
32+
"execution_count": null,
33+
"metadata": {},
34+
"outputs": [],
35+
"source": [
36+
"def pdf_to_jpg(pdf_path, output_path=\"converted_image.jpg\"):\n",
37+
" \"\"\"\n",
38+
" Convert the first page of a PDF to a JPG image.\n",
39+
"\n",
40+
" Args:\n",
41+
" pdf_path (str): Path to the input PDF file.\n",
42+
" output_path (str): Path to save the converted JPG image.\n",
43+
"\n",
44+
" Returns:\n",
45+
" str: Path to the saved JPG image.\n",
46+
" \"\"\"\n",
47+
" # Convert the first page of the PDF to an image\n",
48+
" images = convert_from_path(pdf_path, first_page=1, last_page=1)\n",
49+
" if images:\n",
50+
" images[0].save(output_path, format=\"JPEG\")\n",
51+
" return output_path\n",
52+
" else:\n",
53+
" raise ValueError(\"No pages found in the PDF file.\")"
54+
]
55+
},
56+
{
57+
"cell_type": "markdown",
58+
"metadata": {},
59+
"source": [
60+
"Set up the values for the endpoint and api key."
61+
]
62+
},
63+
{
64+
"cell_type": "code",
65+
"execution_count": null,
66+
"metadata": {},
67+
"outputs": [],
68+
"source": [
69+
"try:\n",
70+
" endpoint = \"\"\n",
71+
" key = \"\"\n",
72+
"except KeyError:\n",
73+
" print(\"Missing environment variable 'VISION_ENDPOINT' or 'VISION_KEY'\")\n",
74+
" print(\"Set them before running this sample.\")"
75+
]
76+
},
77+
{
78+
"cell_type": "markdown",
79+
"metadata": {},
80+
"source": [
81+
"Set up an Image Analysis client."
82+
]
83+
},
84+
{
85+
"cell_type": "code",
86+
"execution_count": null,
87+
"metadata": {},
88+
"outputs": [],
89+
"source": [
90+
"client = ImageAnalysisClient(\n",
91+
" endpoint=endpoint,\n",
92+
" credential=AzureKeyCredential(key)\n",
93+
")"
94+
]
95+
},
96+
{
97+
"cell_type": "markdown",
98+
"metadata": {},
99+
"source": [
100+
"Initiate the image."
101+
]
102+
},
103+
{
104+
"cell_type": "code",
105+
"execution_count": null,
106+
"metadata": {},
107+
"outputs": [],
108+
"source": [
109+
"#image_path = \"200.jpg\"\n",
110+
"\n",
111+
"image_path = pdf_to_jpg(\"200_tegnforklaring.pdf\")\n",
112+
"\n",
113+
"with open(image_path, \"rb\") as f:\n",
114+
" image_data = f.read()"
115+
]
116+
},
117+
{
118+
"cell_type": "markdown",
119+
"metadata": {},
120+
"source": [
121+
"Define the visual features you want to analyze."
122+
]
123+
},
124+
{
125+
"cell_type": "code",
126+
"execution_count": null,
127+
"metadata": {},
128+
"outputs": [],
129+
"source": [
130+
"visual_features =[\n",
131+
" VisualFeatures.TAGS,\n",
132+
" VisualFeatures.OBJECTS,\n",
133+
" VisualFeatures.CAPTION,\n",
134+
" VisualFeatures.DENSE_CAPTIONS,\n",
135+
" VisualFeatures.READ,\n",
136+
" VisualFeatures.SMART_CROPS,\n",
137+
" VisualFeatures.PEOPLE,\n",
138+
"]"
139+
]
140+
},
141+
{
142+
"cell_type": "markdown",
143+
"metadata": {},
144+
"source": [
145+
"Analyze the image using the analyze method."
146+
]
147+
},
148+
{
149+
"cell_type": "code",
150+
"execution_count": null,
151+
"metadata": {},
152+
"outputs": [],
153+
"source": [
154+
"result = client.analyze(\n",
155+
" image_data=image_data,\n",
156+
" visual_features=visual_features,\n",
157+
" gender_neutral_caption=True, \n",
158+
" language=\"en\"\n",
159+
")"
160+
]
161+
},
162+
{
163+
"cell_type": "markdown",
164+
"metadata": {},
165+
"source": [
166+
"Print all the analysis results."
167+
]
168+
},
169+
{
170+
"cell_type": "code",
171+
"execution_count": null,
172+
"metadata": {},
173+
"outputs": [],
174+
"source": [
175+
"print(\"Image analysis results:\")\n",
176+
"\n",
177+
"if result.caption is not None:\n",
178+
" print(\" Caption:\")\n",
179+
" print(f\" '{result.caption.text}', Confidence {result.caption.confidence:.4f}\")\n",
180+
"\n",
181+
"if result.dense_captions is not None:\n",
182+
" print(\" Dense Captions:\")\n",
183+
" for caption in result.dense_captions.list:\n",
184+
" print(f\" '{caption.text}', {caption.bounding_box}, Confidence: {caption.confidence:.4f}\")\n",
185+
"\n",
186+
"if result.read is not None:\n",
187+
" print(\" Read:\")\n",
188+
" for line in result.read.blocks[0].lines:\n",
189+
" print(f\" Line: '{line.text}', Bounding box {line.bounding_polygon}\")\n",
190+
" for word in line.words:\n",
191+
" print(f\" Word: '{word.text}', Bounding polygon {word.bounding_polygon}, Confidence {word.confidence:.4f}\")\n",
192+
"\n",
193+
"if result.tags is not None:\n",
194+
" print(\" Tags:\")\n",
195+
" for tag in result.tags.list:\n",
196+
" print(f\" '{tag.name}', Confidence {tag.confidence:.4f}\")\n",
197+
"\n",
198+
"if result.objects is not None:\n",
199+
" print(\" Objects:\")\n",
200+
" for object in result.objects.list:\n",
201+
" print(f\" '{object.tags[0].name}', {object.bounding_box}, Confidence: {object.tags[0].confidence:.4f}\")\n",
202+
"\n",
203+
"if result.people is not None:\n",
204+
" print(\" People:\")\n",
205+
" for person in result.people.list:\n",
206+
" print(f\" {person.bounding_box}, Confidence {person.confidence:.4f}\")\n",
207+
"\n",
208+
"if result.smart_crops is not None:\n",
209+
" print(\" Smart Cropping:\")\n",
210+
" for smart_crop in result.smart_crops.list:\n",
211+
" print(f\" Aspect ratio {smart_crop.aspect_ratio}: Smart crop {smart_crop.bounding_box}\")\n",
212+
"\n",
213+
"print(f\" Image height: {result.metadata.height}\")\n",
214+
"print(f\" Image width: {result.metadata.width}\")\n",
215+
"print(f\" Model version: {result.model_version}\")"
216+
]
217+
}
218+
],
219+
"metadata": {
220+
"kernelspec": {
221+
"display_name": "Python 3",
222+
"language": "python",
223+
"name": "python3"
224+
},
225+
"language_info": {
226+
"name": "python",
227+
"version": "3.13.0"
228+
}
229+
},
230+
"nbformat": 4,
231+
"nbformat_minor": 2
232+
}

0 commit comments

Comments
 (0)