Latest Contributions by VHolubec

‎01-08-2020

Dear Ismael Chivite‌, what is the future of AuGeo? Is there any roadmap? I found some answer on github from fall, that the development was stopped. It would be a great pity. AuGEO seems great for us, and we would like to show to our customers especially who works with underground utilities. Thank you. Regards, Vladimir

‎01-08-2020

Dear all, please could you consider add a function to set coordinate system, when creating new/empty feature layer in ArcGIS Online from template? This option is added to workflow when you are creating the feature layer from developers.arcgis.com, but it´s missing in ArcGIS Online. Some basic users, who using just AGOL missing so much this functionality, because they are missing the option to create a new feature layer in native (and mandatory) coordinate system - like S-JTKS (5514). Now they use Desktop or non-Esri thick client to create FGDB or SHP in JTSK which then upload to ArcGIS Online. Usage the Developers page is for some user misleading (why we should use another page - we want just to use ArcGIS Online). So, for user experience it would be great to add this capability also to ArcGIS Online itself and increase the value of the usage of the ArcGIS Online itself for some easier tasks, where the thick client is so complex to use. For example (use case) - I would like to gather with Collector damaged trash cans. I must do this in JTSK. So the desired workflow is to create a new empty hosted feature layer in ArcGIS Online IN JTKS, then add the new layer to map, collect data in Collector and then visualize them in map. Everything in one box in ArcGIS Online. Thank you. Vladimir

‎12-06-2019

Dear Adena Schutzberg great thank you. Just as a future option, please try to consider further instructor-led training or bootcamps. I would be great to learn more about deep learning. I am looking forward to course you mentioned. Have a great day. Regards, Vladimir

‎12-05-2019

Dear all, do you plan some Bootcamp or instructor led training for Deep Learning in ArcGIS pro or Python API. Or at least any MOOC for this subject? Thank you. Regards, Vladimir

‎12-02-2019

Dear Sandeep Kumar, with this settings it works. The problem is, that it seems to me so coarse (in comparision to previous settings) - see and the batch looks like this - no so ideal - no on every chips the pools is highlighted. Please could you explain, why the ptevious settings did not work? Is there any limit to chip size and number of chips, which Python API could handle? Thank you, Vladimir

‎12-02-2019

Dear Sandeep Kumar, I am learning a model for pools. When I set bigger chip size, I am not able to get to detail like the attached one. - the size is 200 to 200 pixels and cell size 0.045 (because the map is in WebMercator, I believe it´s in meters - am I right? ) - and the real size of the area is around 10x meters. If I set the chip to 256x256 and pixel size to 0.2, I don´t think the resul is usable - see So I don´t know, if there is any other way, how to set the export of training chips more proper way? The error I mentioned in the initial post - have you seen this? It seems for me some issue with the chips themselves. - RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. pls help - PyTorch Forums but I have no idea, how to identified the bad chips. Thank you for any ideas. Regards, Vladimir

‎11-29-2019

Dear all, I have issue with deep learning tools. I exported 12 000 training chips from Esri Imagery basemap to TIFF - see settings.png The TIFFs looks fine as well as the labels file. On calling data = prepare_data(data_path, class_mapping={1:'Pool'}, batch_size=64) I am getting error - UserWarning: It's not possible to collate samples of your dataset together in a batch. warn(message) For data.show_batch() - now I am getting result - RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 19 and 10 in dimension 3 at ..\aten\src\TH/generic/THTensor.cpp:711 I am not sure what does it mean? Does the Export training data tool corrupt some chips? Is there a way how to find out which chips are corrupted? Or how to fix it? The chips were created in PRO by Export training data tool, so these could be fine. Thank you for any idea. Vladimir

‎11-12-2019

Dear Shaun, ok, thank you. I will duplicate this issue to the github. Thank you for help.

‎11-11-2019

Dear Shaun, this issue I met in Jupyter from PRO Final 2.4. I don´t know now, what Learn Module version was there. Testing on 2.5 is still on my To-Do list.

‎11-04-2019

This would be really great. Now the inability to set what will be in the header of the statistic pop-up is confusing for user.

‎10-31-2019

Dear Dan, It CC 3.0 would be supported by PyTorch - the NVIDIA CUUDA K4000 should works fine by - CUDA - Wikipedia. But as Shaun Walbridge wrote CC 3.5 is needed and there K4000 is really not supported.

‎10-31-2019

Dear Shaun, I am sorry for my late answer. I am testing it on 2.5 Beta - but there I am having another issues in jupyter where learn module is unable to load required fastai and other packages (even if these packages are installed) - another story. data.show_batch() shows just the warning and nothing more. The same error was raised for ssd = SingleShotDetector(). I tried to install CPU based packages, but it ended up with another error - so I have to left this way. If CUDA Compute capability 3.5 support is needed - it should be documented somewhere in Esri documentation. I cannot find it there. It could mislead some users. Have a great day. Regards, Vladimir

‎10-22-2019

Dear Dan, I tried to reinstall pytorch from pytorch channel - -c pytorch pytorch=1.0.0, but it does not install further packages. I am installing this version since I am using the workflow from Rohit Singh here - https://medium.com/geoai/how-we-did-it-end-to-end-deep-learning-in-arcgis-dd5b10d87b8, so I don´t know If I can use the older package of pytorch. Also I tried to install manually pytorch-cpu packages, but it did not help and I was not able to use - data.show_batch() function from deep learning module. It seems that for using esri deep learning module, you need a newer GPU - on another machine with Quadro M2000 - which running on newer core that K4000, it works fine.

‎10-21-2019

Dear Dan, cannot find the switch from GPU to CPU libs for esri Python deep learning module.

‎10-20-2019

Dear Robert, I don´t use PyTorch directly - but via Python API (learn module) or ArcGIS PRO. For both, when using tools for deep learning you are need Pytorch installed. The problem is, that these tools does not run on older graphic cards - for example as is Quadro K4000. Which support CUDA, but just only some older version. I cannot find what version of CUDA the supported graphic card must support and if there any workaround for Python API and ArcGIS PRO to use deep learning tools in machine with this older GPU. Thank you for any idea.

Online Status	Offline
Date Last Visited	yesterday

My Ideas

Latest Contributions by VHolubec

Re: AuGeo: An Augmented Reality mobile app for your GIS data

Set coordinate system when creating New Feature layer in ArcGIS Online

Re: Courses for Deep Learning

Courses for Deep Learning

Re: Deep learning - invalid argument 0: Sizes of tensors must match except in dimension 0

Re: Deep learning - invalid argument 0: Sizes of tensors must match except in dimension 0

Deep learning - invalid argument 0: Sizes of tensors must match except in dimension 0

Re: Deep Learning graphic card requirement

Re: Deep Learning graphic card requirement

Re: Simpler map pop-ups in Insights

Re: Deep Learning graphic card requirement

Re: Deep Learning graphic card requirement

Re: Deep Learning graphic card requirement

Re: Deep Learning graphic card requirement

Re: Deep Learning graphic card requirement

Has anyone encountered issue with importing arcgis...

ArcGIS Pro - Consider adding an integrated 3D obje...

Re: Has anyone encountered issue with importing ar...

Re: Pop-up okna ve WMS vrstvách DMVS

Re: School Bundle - analýza map viewer neexistuje?