POST
|
This occurs when there are no detections during inferencing. Is the cell size of the training samples and the image you used for inferencing, the same? One issue can also be the threshold is too high, but at 0.1 nothing should get filtered (so that's not an issue). if you are running this using your gpu, can you try doing the same using your CPU (change it on the environments tab of the tool)
... View more
04-13-2021
09:05 AM
|
1
|
0
|
1863
|
POST
|
Landsat data should not be 32 bit floating point. At what point did it get converted? you can apply a stretch function to convert it to 8 bit, and then do all your processing in 8 bit space. I also noticed you forced a learning rate (for training). Any particular reason? The stride size is blank above - I'd recommend having some overlap. Regarding running into out of memory issues, with a batch size of 2, and tile size of 256, you shouldn't run into that issue. Which GPU do you have? If you still run into issues, we can connect directly and I can help out over a screenshare.
... View more
04-12-2021
08:34 AM
|
0
|
2
|
5195
|
POST
|
Which release are you on? Pro 2.7 enables you to work with sparse training samples and more than 3 bands (more than 3 bands was not supported before that). Next - here are some pointers for your workflows. 1. Capture training samples that are representative of your regions of interest. eg: 2. Ensure the output image format for your 'Export Training Data for Deep Learning' GP tool is Tiff. your metadata format should be classified tiles 3. When filling in the parameters for the 'Train Deep Learning Model' tool , set your model type to u-net. Ensure you set ignore_classes = 0 ( in the model arguments section) 4. Lastly - run the pixel classification tools and you should ideally get the results you need. you can go through the process and increase the number of samples if needed. If things still dont work - can you provide this information: - how many bands does your input data have? - what is the bit depth of your input data? - Are you using CPU or GPU for computing? - Which software release are you running this on? - did you try other models (DeepLab for instance)
... View more
04-09-2021
12:33 PM
|
0
|
0
|
5217
|
POST
|
Hi Todd, You need ArcGIS Pro 2.7 for this model to run.
... View more
03-15-2021
10:28 AM
|
1
|
1
|
1054
|
BLOG
|
Hi Geunter - yes we have a notebook referenced already. in the point cloud item
... View more
10-14-2020
09:19 AM
|
0
|
0
|
1726
|
BLOG
|
With the firehose of imagery that’s streaming down daily from a variety of sensors, the need for using AI to automate feature extraction is only increasing. To make sure your organization is prepared, Esri is taking AI to the next level. We are very excited to announce the release of ready-to-use geospatial AI models on the ArcGIS Living Atlas. Article Overview: Esri is bringing ready-to-use deep learning models to our user community through ArcGIS Online. To kick it off, we’ve added three models — building footprint extraction and land cover classification from satellite imagery, and another model to classify points representing trees in point cloud datasets. With the existing capabilities in ArcGIS, you’ve been able to train over a dozen deep learning models on geospatial datasets and derive information products using the ArcGIS API for Python or ArcGIS Pro, and scale up processing using ArcGIS Image Server. Building footprints automatically extracted using the new deep learning model These newly released models are a game changer! They have been pre-trained by Esri on huge volumes of data and can be readily used (no training required!) to automate the tedious task of digitizing and extracting geographical features from satellite imagery and point cloud datasets. They bring the power of AI and deep learning to the Esri user community. What’s more, these deep learning models are accessible for anyone with an ArcGIS Online subscription at no additional cost. Using the models Using these models is simple. You can use geoprocessing tools (such as the Detect Objects Using Deep Learning tool) in ArcGIS Pro with the imagery models. Point the tool to the imagery and the downloaded model, and that’s about it – deep learning has never been this easy! A GPU, though not necessary, can help speed things up. With ArcGIS Enterprise, you can scale up the inferencing using Image Server. Using the building footprint extraction model in ArcGIS Pro Coming soon, you’ll be able to consume the model directly in ArcGIS Online Imagery and run it against your own uploaded imagery—all without an ArcGIS Enterprise deployment. The 3D Basemaps solution is also being enhanced to use the tree point classification model and create realistic 3D tree models from raw point clouds. How can you benefit from these deep learning models? It probably goes without saying that manually extracting features from imagery—like digitizing footprints or generating land cover maps—is time-consuming. Deep learning automates the process and significantly minimizes the manual interaction needed to create these products. However, training your own deep learning model can be complicated – it needs a lot of data, extensive computing resources, and knowledge of how deep learning works. Sample building footprints extracted - Woodland, CA With ready-to-use models, you no longer have to invest time and energy into manually extracting features or training your own deep learning model. These models have been trained on data from a variety of geographies and work well across them. As new imagery comes in, you can readily extract features at the click of a button, and produce layers of GIS datasets for mapping, visualization and analysis. Sample building footprints extracted - Palm Islands, Dubai Get to know the first three models we released Three deep learning models are now available in ArcGIS Online. (Watch for more models in the future!). These models are available as deep learning packages (DLPKs) that can be used with ArcGIS Pro, Image Server and ArcGIS API for Python. 1. Building Footprint Extraction model is used to extract building footprints from high resolution satellite imagery. While its designed for the contiguous United States, it performs fairly well in other parts of the globe. The model performs fairly well in other parts of the globe. Results from Ulricehamn, Sweden. Here’s a story map presenting some of the results. Building footprint layers are useful for creating basemaps and in analysis workflows for urban planning and development, insurance, taxation, change detection, and infrastructure planning. 2. Landcover Classification model is used to create a land cover product using Landsat 8 imagery. The classified land cover will have the same classes as the National Land Cover Database. The resulting land cover maps are useful for urban planning, resource management, change detection and agriculture. Classified landcover map using Landsat 8 imagery This generic model is has been trained on the National Land Cover Database (NLCD) 2016 with the same Landsat 8 scenes that were used to produce the database. Land cover classification is a complex exercise and is hard to capture using traditional means. Deep learning models have a high capacity to learn these complex semantics and give superior results. 3. Tree Point Classification model can be used to classify points representing trees in point cloud datasets. 3D scene created by employing tree point classification model. Classifying tree points is useful for creating high quality 3D basemaps, urban planning and forestry workflows. Next steps Try out the deep learning models in ArcGIS Living Atlas for yourself. Read more detailed instructions for using the deep learning models in ArcGIS. Have questions? Let us know on GeoNet how they are working for you, and which other feature extraction tasks you’d like AI to do for you!
... View more
10-14-2020
08:31 AM
|
0
|
3
|
2304
|
POST
|
Can you bring up the task manager and see if your GPU is being used? What is the activity (percent use) of the CPU and GPU?
... View more
08-06-2020
11:24 AM
|
0
|
0
|
729
|
POST
|
Once you do the labelling, can you do the exporting of training data, using the Export Training Data for Deep Learning GP tool?
... View more
07-29-2020
06:03 PM
|
1
|
0
|
915
|
POST
|
Looks like you've got the syntax incorrect. Using this syntax should work (I’ve used variables, so you can directly just use this command line). (Pro 2.6) arcpy.ia.ExportTrainingDataForDeepLearning(inRaster, out_folder, in_training, image_chip_format, tile_size_x, , tile_size_y, stride_x, stride_y, "ONLY_TILES_WITH_FEATURES", metadata_format, 0, None, 0, None, 0, reference_system, "PROCESS_AS_MOSAICKED_IMAGE", "NO_BLACKEN", "FIXED_SIZE")
... View more
07-29-2020
06:00 PM
|
1
|
0
|
938
|
POST
|
1 of 2 problems: You've shared the mosaic dataset by reference and the server cant see the path. Or – whats quite likely the issues is the image paths are broken. Can you navigate to the location in the screenshot and see if you can load those files? The folder connection in his screenshots do not show any unc paths, but the analyzer shows UNC paths (in your screenshot). So something is suspect. You probably connected to a unc path and are trying to publish a mosaic dataset which has an absolute path, which is causing the error it looks like. In your scenario, I would analyze the mosaic dataset before publishing, to ensure the mosaic dataset is clean. Then we can see if it’s a server issue (server doesn’t have permissions to the mosaic dataset/datasets) as step 2 Also based on the error code in the screenshot - see this - https://pro.arcgis.com/en/pro-app/help/sharing/analyzer-warning-messages/24016-mosaic-dataset-contains-error-found-during-item-level-analysis.htm For all MD analyzer errors – see https://pro.arcgis.com/en/pro-app/help/data/imagery/mosaic-dataset-analyzer-error-70113.htm
... View more
07-29-2020
05:58 PM
|
4
|
1
|
638
|
POST
|
Can you follow these steps to install the framework? Install deep learning frameworks for ArcGIS—ArcGIS Pro | Documentation The error message states there's a missing dpeendancy. It could very well also be you have installed the relevant python modules to the new cloned enviornment, but its not your active python environment and hence the failures
... View more
04-29-2020
08:51 AM
|
0
|
0
|
1025
|
POST
|
Please try these steps for installation Install deep learning frameworks for ArcGIS—ArcGIS Pro | Documentation Also - which locale is your system set to? (US English?)
... View more
04-29-2020
08:50 AM
|
0
|
3
|
766
|
POST
|
Hi - You typically run into this issue, if you dont have an image selected in your contents pane. regards, Vinay
... View more
04-27-2020
04:49 PM
|
0
|
0
|
1493
|
POST
|
Hey Bahram - Please use RCNN as the metadata format when exporting your training samples, as you are trying to delineate building footprint (and not just derive bounding polygons around buildings). Also when running the train deep learning model tool, explicitly, change the model type parameter (it will be blank by default which is causing your error messafe)and that should solve your problem Regards, Vinay
... View more
04-27-2020
04:47 PM
|
1
|
2
|
1184
|
POST
|
here are currently two options for using stereo in Pro (apart from the red/blue glasses): Single display setup using NVidia 3D vision This is a cheaper single monitor (for stereo) setup that uses active shutter glasses. Requires a NVidia card that support 3D vision, a 120Hz monitor that supports 3D vision and a 3D vision kit (glasses and emitter). This setup requires 3D vision drivers that are only installed with Release 418 (or lower) drivers from Nvidia. Instructions for setting these up can be found in Pro’s help. Keep in mind you can use additional displays along with the one for stereo that do not need to be 120Hz 3D vision displays. We have a 3 monitor setup that uses one 3D vision monitor along with 2 normal monitors. Multi-display setup like Planar/Pluraview 3D This is a multiple monitor setup in a proprietary rig that use passive glasses. They can be used with either Nvidia or AMD graphics cards. Graphics card recommendations and setup instructions are provided by the vendors website. The glasses are usually supplied with monitors themselves. ArcGIS Pro’s shutter glass mode supports this kind of setup as well. You can also use other monitors along with this setup too.
... View more
03-31-2020
10:36 PM
|
0
|
1
|
787
|
Title | Kudos | Posted |
---|---|---|
1 | 08-29-2022 01:16 PM | |
2 | 08-05-2022 08:23 AM | |
1 | 04-13-2021 09:05 AM | |
1 | 10-13-2021 08:26 AM | |
1 | 02-21-2019 02:04 PM |
Online Status |
Offline
|
Date Last Visited |
a week ago
|