Skip to content

Commit f2beacc

Browse files
DavidJVitaleDavidJVitale
authored
Merge pull request #583 from jyaistMap/jy-release-notes-171
Release notes for the 1.7.1 release
2 parents 43de8de + ca80d30 commit f2beacc

File tree

1 file changed

+190
-1
lines changed

1 file changed

+190
-1
lines changed

‎guide/02-api-overview/release-notes.ipynb

Lines changed: 190 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,194 @@
11
{
22
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {},
6+
"source": [
7+
"# What's new in version 1.7.1"
8+
]
9+
},
10+
{
11+
"cell_type": "markdown",
12+
"metadata": {},
13+
"source": [
14+
"## New"
15+
]
16+
},
17+
{
18+
"cell_type": "markdown",
19+
"metadata": {},
20+
"source": [
21+
"### New Samples"
22+
]
23+
},
24+
{
25+
"cell_type": "markdown",
26+
"metadata": {},
27+
"source": [
28+
"* [Automate Road Surface Investigation Using Deep Learning](https://developers.arcgis.com/python/sample-notebooks/automate_road_surface_investigation_using_deep_learning)\n",
29+
"* [Detecting and Categorizing Brick Kilns from Satellite Imagery](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/detecting_and_categorizing_brick_kilns_from_satellite_imagery.ipynb)\n",
30+
"* [Extracting Slums from Satellite Imagery](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/extracting_slums_from_satellite_imagery.ipynb)\n",
31+
"* [Extracting Sinkholes from Aerial Imagery](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/extracting_sinkholes_from_aerial_imagery_over_deadsea)\n",
32+
"* [Detecting Settlements Using Supervised Classification and Deep Learning](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/detecting_settlements_using_landsat-8_imagery)\n",
33+
"* [How much green is Delhi as on 15 Oct 2017?](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/how-much-green-is-Delhi-as-on-15-oct-2017) \n",
34+
"* [Maximizing Fire Protection Coverage](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/site_maximizes_fire_protection_coverage)\n",
35+
"* [Calculate Impervious Surfaces from Multispectral Imagery using Deep Learning](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/calculate_impervious_surfaces_from_multispectral_imagery/)\n",
36+
"* [Safe Streets to Schools](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/safe_streets_to_schools)\n",
37+
"* [Spatial and temporal distribution of service calls using big data tools](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/spatial_and_temporal_trends_of_service_calls)\n",
38+
"* [Time Series Prediction of AirBnB Properties in New York City](https://developers.arcgis.com/python/samples/04_gis_analysts_data_scientists/analyzing_growth_factors_of_airbnb_properties_in_new_york_city)"
39+
]
40+
},
41+
{
42+
"cell_type": "markdown",
43+
"metadata": {},
44+
"source": [
45+
"#### [`arcgis.raster.functions.gbl`](https://developers.arcgis.com/python/api-reference/arcgis.raster.functions.gbl.html#)"
46+
]
47+
},
48+
{
49+
"cell_type": "markdown",
50+
"metadata": {},
51+
"source": [
52+
"New functions\n",
53+
" * [`corridor`](https://developers.arcgis.com/python/api-reference/arcgis.raster.functions.gbl.html#corridor)"
54+
]
55+
},
56+
{
57+
"cell_type": "markdown",
58+
"metadata": {},
59+
"source": [
60+
"#### [`arcgis.env`](https://developers.arcgis.com/python/api-reference/arcgis.env.html)"
61+
]
62+
},
63+
{
64+
"cell_type": "markdown",
65+
"metadata": {},
66+
"source": [
67+
"* new parameter `type_init_tail_parameters` (See [`arcgis.learn`](#arcgis.learn) below.)"
68+
]
69+
},
70+
{
71+
"cell_type": "markdown",
72+
"metadata": {},
73+
"source": [
74+
"#### [`arcgis.learn`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html)"
75+
]
76+
},
77+
{
78+
"cell_type": "markdown",
79+
"metadata": {},
80+
"source": [
81+
"* Adds support for multiple GPU machines to `learn` module\n",
82+
"* Adds the [`DeepLabV3`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#deeplab) model based on [`torchvision`](https://pytorch.org/docs/stable/torchvision/index.html)\n",
83+
" * includes multispectral data support\n",
84+
"* Enhancements to Multispectral data support: \n",
85+
" * turn on `DRA` with the `statistics_type` parameter in various `show_results()` and `show_batch()` functions\n",
86+
" * adds environment variable `type_init_tail_parameters` to control `Model Tail` initialization for `arcgis.learn` functions\n",
87+
"* Sanctions [`classify_objects()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#classify-objects) over [`FeatureClassifier.categorize_features()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.FeatureClassifier.categorize_features) for feature categorization\n",
88+
"* Adds support for training models on either cpu or gpu devices\n",
89+
"* Adds support for evaluating MaskRCNN model performance with correct metrics for the trained model to compare the results\n",
90+
"* Adds [`accuracy()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.UnetClassifier.accuracy) function to [`UnetClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#unetclassifier)\n",
91+
"* Adds `unet_aux_loss` parameter to the [`PSPNetClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#pspnetclassifier)\n",
92+
"* Adds support for training a subset of classes from [`prepare_data()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#prepare-data) `class_mapping` parameter to [`MaskRCNN`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#maskrcnn)\n",
93+
"* Adds multispectral data support to:\n",
94+
" * [`FeatureClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#featureclassifier)\n",
95+
" * [`SingleShotDetector`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#singleshotdetector)\n",
96+
" * [`RetinaNet`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#retinanet)\n",
97+
" * [`PSPNetClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#pspnetclassifier)\n",
98+
" * [`MaskRCNN`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#maskrcnn)\n",
99+
"* Adds support for `resnet18` and `resnet34` backbones to [`MaskRCNN`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#maskrcnn)\n",
100+
"* Adds support for `batchnorm` unfreezing in * [`PSPNetClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#pspnetclassifier)\n",
101+
"* Adds support for panchromatic data\n",
102+
"* Adds validation to `class_mapping` parameter for [`prepare_data()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#prepare-data) function"
103+
]
104+
},
105+
{
106+
"cell_type": "markdown",
107+
"metadata": {},
108+
"source": [
109+
"## Fixes"
110+
]
111+
},
112+
{
113+
"cell_type": "markdown",
114+
"metadata": {},
115+
"source": [
116+
"#### [`arcgis.gis.admin`](https://developers.arcgis.com/python/api-reference/arcgis.gis.admin.html)"
117+
]
118+
},
119+
{
120+
"cell_type": "markdown",
121+
"metadata": {},
122+
"source": [
123+
"* Fixes formatting in [`EnterpriseUsers.update()`](https://developers.arcgis.com/python/api-reference/arcgis.gis.admin.html#arcgis.gis.admin.EnterpriseUsers.update) function"
124+
]
125+
},
126+
{
127+
"cell_type": "markdown",
128+
"metadata": {},
129+
"source": [
130+
"#### [`arcgis.mapping`](https://developers.arcgis.com/python/api-reference/arcgis.mapping.html)"
131+
]
132+
},
133+
{
134+
"cell_type": "markdown",
135+
"metadata": {},
136+
"source": [
137+
"* Fixes error when drawing [`map widget`](https://developers.arcgis.com/python/api-reference/arcgis.widgets.html#mapview) using Microsoft Edge"
138+
]
139+
},
140+
{
141+
"cell_type": "markdown",
142+
"metadata": {},
143+
"source": [
144+
"#### [`arcgis.raster.functios.gbl`](https://developers.arcgis.com/python/api-reference/arcgis.raster.functions.gbl.html#)"
145+
]
146+
},
147+
{
148+
"cell_type": "markdown",
149+
"metadata": {},
150+
"source": [
151+
"* General improvements to documentation\n",
152+
"* Improves alphabetical ordering of [API Reference](https://developers.arcgis.com/python/api-reference/)"
153+
]
154+
},
155+
{
156+
"cell_type": "markdown",
157+
"metadata": {},
158+
"source": [
159+
"#### [`arcgis.learn`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html)"
160+
]
161+
},
162+
{
163+
"cell_type": "markdown",
164+
"metadata": {},
165+
"source": [
166+
"* Improves error messaging when calling `from_model()` if proper libraries are not installed\n",
167+
"* Deprecates the [`FeatureClassifier.categorize_features()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.FeatureClassifier.categorize_features) method in favor of [`classify_objects()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#classify-objects)\n",
168+
"* Improves messaging when `input_video_path` parameter video does not exist for [`RetinaNet.predict_video()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html?highlight=predict_video#arcgis.learn.RetinaNet.predict_video) and [`SingleShotDetector.predict_video()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html?highlight=predict_video#arcgis.learn.SingleShotDetector.predict_video) functions\n",
169+
"* Fixes bug when re-running a previously saved [`SingleShotDetector`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html?highlight=predict_video#singleshotdetector) model\n",
170+
"* Fixes various model inferencing errors when using [`Image Server`](https://enterprise.arcgis.com/en/server/latest/get-started/windows/what-is-arcgis-image-server-.htm)\n",
171+
"* Fixes errors when using [`detect_objects()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html?highlight=predict_video#detect-objects) when raster function configuration information is inaccessible\n",
172+
"* Fixes error when running [`detect_objects()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html?highlight=predict_video#detect-objects) when using no `model_arguments`\n",
173+
"* Fixes [`EntityRecognizer.extract_entities()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html?highlight=predict_video#arcgis.learn.EntityRecognizer.extract_entities) returning a data frame with an empty column name\n",
174+
"* Improves messaging when incorrect path passed as `path` argument to [`prepare_data()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#prepare-data)\n",
175+
"* Fixes error when list of tensors is empty when running [`SingleShotDetector.fit()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.SingleShotDetector.fit) model\n",
176+
"* Fixes model accuracy function in [`Unet`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#unetclassifier) and [`PSPNet`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#pspnetclassifier) to return maximum accuracy if checkpoint is `True`\n",
177+
"* Improves tagging scheme documentation for [`prepare_data()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#prepare-data) function\n",
178+
"* Improves visual accuracy when using Multispectral imagery with [`UNetClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#unetclassifier)\n",
179+
"* Fixes missing `supported_backbone` documentation for all models\n",
180+
"* Improves [`predict()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.FeatureClassifier.predict) and [`from_model()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.FeatureClassifier.from_model) documentation on the [`FeatureClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#featureclassifier)\n",
181+
"* Fixes [`show_batch()`] errors on data objects when [`class_mapping` ](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.prepare_data) parameter values from `prepare_data()`are non-contiguous\n",
182+
"* Fixes errors with `show_results()` and `fit()` methods of [`EntityRecognizer`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#entityrecognizer)\n",
183+
"* Fixes error when `prepare_data()` `dataset_type` argument value is `BILUO`\n",
184+
"* Fixes [`extract_entities()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html?highlight=predict_video#arcgis.learn.EntityRecognizer.extract_entities) error when reading `UTF-16` encoded files\n",
185+
"* Fixes to `load()` function for input paths\n",
186+
"* Fixes error reading file names in [`EntityRecognizer.load()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.EntityRecognizer.load)\n",
187+
"* Fixes error causing `accuracy()` to always return 1 with certain `class_mapping` values when using [`UnetClassifier`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#unetclassifier)\n",
188+
"* Fixes error where color map values were truncated using [`MaskRCNN`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#maskrcnn)\n",
189+
"* Fixes error in [`SingleShotDetector.save()`](https://developers.arcgis.com/python/api-reference/arcgis.learn.html#arcgis.learn.SingleShotDetector.save) method by adding optional `overwrite` parameter"
190+
]
191+
},
3192
{
4193
"cell_type": "markdown",
5194
"metadata": {},
@@ -1187,7 +1376,7 @@
11871376
"name": "python",
11881377
"nbconvert_exporter": "python",
11891378
"pygments_lexer": "ipython3",
1190-
"version": "3.6.8"
1379+
"version": "3.6.9"
11911380
},
11921381
"varInspector": {
11931382
"cols": {

0 commit comments

Comments
 (0)