|
2 | 2 | "cells": [
|
3 | 3 | {
|
4 | 4 | "cell_type": "markdown",
|
5 |
| - "id": "3966ea30", |
6 | 5 | "metadata": {},
|
7 | 6 | "source": [
|
8 | 7 | "# Use MMDetection with `arcgis.learn`"
|
9 | 8 | ]
|
10 | 9 | },
|
11 | 10 | {
|
12 | 11 | "cell_type": "markdown",
|
13 |
| - "id": "fc0b15f6", |
14 | 12 | "metadata": {},
|
15 | 13 | "source": [
|
16 | 14 | "## Introduction"
|
17 | 15 | ]
|
18 | 16 | },
|
19 | 17 | {
|
20 | 18 | "cell_type": "markdown",
|
21 |
| - "id": "54bff152", |
22 | 19 | "metadata": {},
|
23 | 20 | "source": [
|
24 | 21 | "MMdetection is an open-source library containing many popular and state-of-the-art object detection models. Through `arcgis.learn` we have provided a bridge to use the growing list of models provided by the MMDetection library.\n",
|
|
28 | 25 | },
|
29 | 26 | {
|
30 | 27 | "cell_type": "markdown",
|
31 |
| - "id": "2b2977bf", |
32 | 28 | "metadata": {},
|
33 | 29 | "source": [
|
34 | 30 | "## Setting up the environment"
|
35 | 31 | ]
|
36 | 32 | },
|
37 | 33 | {
|
38 | 34 | "cell_type": "markdown",
|
39 |
| - "id": "73b3647d", |
40 | 35 | "metadata": {},
|
41 | 36 | "source": [
|
42 | 37 | "Follow the steps [here](https://developers.arcgis.com/python/guide/install-and-set-up/#Install-deep-learning-dependencies) to install deep learning dependencies in ArcGIS Pro or the Anaconda environment respectively.\n",
|
|
51 | 46 | },
|
52 | 47 | {
|
53 | 48 | "cell_type": "markdown",
|
54 |
| - "id": "e94dd76c", |
55 | 49 | "metadata": {},
|
56 | 50 | "source": [
|
57 | 51 | "## Implementation in `arcgis.learn`"
|
58 | 52 | ]
|
59 | 53 | },
|
60 | 54 | {
|
61 | 55 | "cell_type": "markdown",
|
62 |
| - "id": "1ae59541", |
63 | 56 | "metadata": {},
|
64 | 57 | "source": [
|
65 | 58 | "Using MMDetection with arcgis.learn is as simple as using any other object detection model in the library. The only additional step is providing the name of the model to be used when initializing the MMDetection model object."
|
|
68 | 61 | {
|
69 | 62 | "cell_type": "code",
|
70 | 63 | "execution_count": null,
|
71 |
| - "id": "b713bb79", |
72 | 64 | "metadata": {},
|
73 | 65 | "outputs": [],
|
74 | 66 | "source": [
|
|
77 | 69 | },
|
78 | 70 | {
|
79 | 71 | "cell_type": "markdown",
|
80 |
| - "id": "153b3511", |
81 | 72 | "metadata": {},
|
82 | 73 | "source": [
|
83 | 74 | "The parameters required are:\n",
|
|
88 | 79 | },
|
89 | 80 | {
|
90 | 81 | "cell_type": "markdown",
|
91 |
| - "id": "54036ae2", |
92 | 82 | "metadata": {},
|
93 | 83 | "source": [
|
94 | 84 | "The following MMDetection models are supported through `arcgis.learn`:"
|
|
97 | 87 | {
|
98 | 88 | "cell_type": "code",
|
99 | 89 | "execution_count": 1,
|
100 |
| - "id": "10a8dcf6", |
101 | 90 | "metadata": {
|
102 | 91 | "scrolled": false
|
103 | 92 | },
|
|
141 | 130 | },
|
142 | 131 | {
|
143 | 132 | "cell_type": "markdown",
|
144 |
| - "id": "a7ee3674", |
145 | 133 | "metadata": {},
|
146 | 134 | "source": [
|
147 | 135 | "The `model` argument can also accept the path to a config file for a variation of one of the supported models. These files can be found [here](https://github.com/open-mmlab/mmdetection/tree/master/configs). The [configs directory](https://github.com/open-mmlab/mmdetection/tree/master/configs) in the mmdetection repository needs to be downloaded for other model variants to work.\n",
|
|
152 | 140 | {
|
153 | 141 | "cell_type": "code",
|
154 | 142 | "execution_count": null,
|
155 |
| - "id": "380b5112", |
156 | 143 | "metadata": {},
|
157 | 144 | "outputs": [],
|
158 | 145 | "source": [
|
|
163 | 150 | },
|
164 | 151 | {
|
165 | 152 | "cell_type": "markdown",
|
166 |
| - "id": "64c92d89", |
167 | 153 | "metadata": {},
|
168 | 154 | "source": [
|
169 | 155 | "## Training and inference"
|
170 | 156 | ]
|
171 | 157 | },
|
172 | 158 | {
|
173 | 159 | "cell_type": "markdown",
|
174 |
| - "id": "3572d6b1", |
175 | 160 | "metadata": {},
|
176 | 161 | "source": [
|
177 | 162 | "The MMdetection models can be trained using the `fit` method. "
|
|
180 | 165 | {
|
181 | 166 | "cell_type": "code",
|
182 | 167 | "execution_count": null,
|
183 |
| - "id": "07e4ec1e", |
184 | 168 | "metadata": {},
|
185 | 169 | "outputs": [],
|
186 | 170 | "source": [
|
|
189 | 173 | },
|
190 | 174 | {
|
191 | 175 | "cell_type": "markdown",
|
192 |
| - "id": "9c9a3ee9", |
193 | 176 | "metadata": {},
|
194 | 177 | "source": [
|
195 | 178 | "Alternatively, [Train Deep Learning Model](https://pro.arcgis.com/en/pro-app/latest/tool-reference/image-analyst/train-deep-learning-model.htm) tool in ArcGIS Pro can be used to train the models.\n",
|
|
198 | 181 | },
|
199 | 182 | {
|
200 | 183 | "cell_type": "markdown",
|
201 |
| - "id": "b30ca095", |
202 | 184 | "metadata": {},
|
203 | 185 | "source": [
|
204 | 186 | "For more information about the API, visit the [API reference for MMDetection](https://developers.arcgis.com/python/api-reference/arcgis.learn.toc.html#mmdetection). For a detailed object detection workflow, refer to a sample [notebook](https://developers.arcgis.com/python/sample-notebooks/detecting-and-categorizing-brick-kilns-from-satellite-imagery/)."
|
205 | 187 | ]
|
206 | 188 | },
|
207 | 189 | {
|
208 | 190 | "cell_type": "markdown",
|
209 |
| - "id": "baa35be8", |
210 | 191 | "metadata": {},
|
211 | 192 | "source": [
|
212 | 193 | "## References"
|
213 | 194 | ]
|
214 | 195 | },
|
215 | 196 | {
|
216 | 197 | "cell_type": "markdown",
|
217 |
| - "id": "0efca58b", |
218 | 198 | "metadata": {},
|
219 | 199 | "source": [
|
220 | 200 | "[1] OpenMmlab, “openmmlab/mmdetection: OpenMMLab Detection Toolbox and Benchmark.,” GitHub. [Online]. Available: https://github.com/open-mmlab/mmdetection/ [Accessed: 20-Jul-2021]."
|
|
237 | 217 | "name": "python",
|
238 | 218 | "nbconvert_exporter": "python",
|
239 | 219 | "pygments_lexer": "ipython3",
|
240 |
| - "version": "3.7.11" |
| 220 | + "version": "3.7.10" |
241 | 221 | }
|
242 | 222 | },
|
243 | 223 | "nbformat": 4,
|
|
0 commit comments