Oleg Dzhimiev committed changes to the Elphel git project :
tensorboard graphs tests

‎Setup (some details)

← Older revision Revision as of 17:07, 6 July 2018 Line 49: Line 49:    # Export paths   # Export paths    <b>~$ export PATH=/usr/local/cuda-9.2/bin${PATH:+:${PATH}}   <b>~$ export PATH=/usr/local/cuda-9.2/bin${PATH:+:${PATH}} −  ~$ export LD_LIBRARY_PATH=/usr/local/cuda-9.2/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}</b></font>+  ~$ export LD_LIBRARY_PATH=/usr/local/cuda-9.2/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}  + ~$ export LD_LIBRARY_PATH=/usr/local/cuda-9.2/extras/CUPTI/lib64/${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}</b></font>     * Install TensorFlow (build from sources for cuda 9.2): * Install TensorFlow (build from sources for cuda 9.2): Oleg

Oleg Dzhimiev committed changes to the Elphel git project :
fixed working in gui

AndreyFilippov committed changes to the Elphel git project :
updating macro mode (preliminary correlation)

AndreyFilippov committed changes to the Elphel git project :
Done with individual quad-cam adjustment using rig "GT" data

AndreyFilippov committed changes to the Elphel git project :
Implemented main camera field correction from the DSI of the dual camera rig.

Oleg Dzhimiev committed changes to the Elphel git project :
refactored, tested for 3D,4D and 5D

Oleg Dzhimiev committed changes to the Elphel git project :
tested only for (t,z,h,w,c) shapes

AndreyFilippov committed changes to the Elphel git project :
Working on fronto objects at long distances in the model

Oleg Dzhimiev committed changes to the Elphel git project :
no shootray = put z at scene's bbox z

Oleg Dzhimiev committed changes to the Elphel git project :
new scripts

‎Setup

← Older revision Revision as of 18:25, 26 June 2018 Line 85: Line 85:    bitbake u-boot device-tree linux-xlnx core-image-elphel393   bitbake u-boot device-tree linux-xlnx core-image-elphel393  </font> </font> −* Poky 2.2 Jethro+* Poky 2.0 Jethro  <font size='2'> <font size='2'> −  git clone https://git.elphel.com/Elphel/elphel393.git # or git clone git@git.elphel.com:Elphel/elphel393.git # if ssh public key is uploaded+  git clone -b jethro https://git.elphel.com/Elphel/elphel393.git # or git clone git@git.elphel.com:Elphel/elphel393.git # if ssh public key is uploaded    # then follow the same steps as for Rocko   # then follow the same steps as for Rocko  </font> </font> Oleg

‎Draft notes

← Older revision Revision as of 17:19, 26 June 2018 (3 intermediate revisions by the same user not shown)Line 2: Line 2:  === Modifications to the SATA code === === Modifications to the SATA code ===  SATA controller subsystem source code is maintained in a [https://git.elphel.com/Elphel/x393_sata x393_sata] repository. SATA controller subsystem source code is maintained in a [https://git.elphel.com/Elphel/x393_sata x393_sata] repository.  +  1. Edit py393sata/create_ahci_registers.py and modify [https://git.elphel.com/Elphel/x393_sata/blob/master/py393sata/create_ahci_registers.py#L35 RID value] 1. Edit py393sata/create_ahci_registers.py and modify [https://git.elphel.com/Elphel/x393_sata/blob/master/py393sata/create_ahci_registers.py#L35 RID value]    Line 24: Line 25:  # Verify bitsteram with the hardware # Verify bitsteram with the hardware  # Commit to git repository # Commit to git repository  +  +  +==Draft notes==  +====Bitstream type?====  +* In fpga-elphel/x393 x393_global.tcl:  +** checks if HISPI is enabled and make some kind of changes  +  +* status_read.v  +** writes fpga bitstream type Oleg

‎pre

← Older revision Revision as of 00:18, 26 June 2018 Line 4: Line 4:     ==Instructions== ==Instructions== −===pre===+===pre (editing files on the boot SD card)=== −* to load bitstream for MT9F002 appropriate changes need to be made to:+* Remove 10389 board if installed (otherwise will have to rewrite eeprom)  +* To load bitstream for MT9F002 appropriate changes need to be made to:  ** device tree ** device tree    <font size=2>set sensors to '''mt9f002''' in ''elphel393-detect_sensors,sensors'' entry</font>   <font size=2>set sensors to '''mt9f002''' in ''elphel393-detect_sensors,sensors'' entry</font>  ** /etc/elphel393/default_10389.xml for setup w/o 10389 or 10389's eeprom otherwise write '''MT9F002''' as application ** /etc/elphel393/default_10389.xml for setup w/o 10389 or 10389's eeprom otherwise write '''MT9F002''' as application  + Application name must be already added to '''/usr/local/autocampars.php'''  * Disable driver * Disable driver    <font size=2>root@elphel393~# touch /etc/elphel393/disable_driver   <font size=2>root@elphel393~# touch /etc/elphel393/disable_driver Oleg

Oleg Dzhimiev committed changes to the Elphel git project :
fixing headless run

AndreyFilippov committed changes to the Elphel git project :
cleanup

Elphel booth at CVPR 2018 Expo

Elphel is presenting at CVPR 2018 EXPO: Long Range Passive 3D Reconstruction System,  providing NN with custom training sets, enabling realtime 3D-aware machine learning systems.

Please visit us at CVPR, Booth 132.

You can also find our presentation and related articles on wiki page https://wiki.elphel.com/wiki/CVPR2018

 

 

← Older revision Revision as of 06:08, 20 June 2018 Line 1: Line 1:  +This page contains links relevant to Elphel presentation at CVPR 2018 Expo.  +  ==Presentation== ==Presentation==  * [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf High Resolution Wide FoV CNN System for Target Classification, Ranging and Tracking (pdf)] * [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf High Resolution Wide FoV CNN System for Target Classification, Ranging and Tracking (pdf)] Olga

← Older revision Revision as of 14:40, 19 June 2018 Line 4: Line 4:  ==3D models demo and image sets== ==3D models demo and image sets==  * [https://community.elphel.com/3d+biquad/?lat=40.74257500&lng=-112.06741333&zoom=10&rating=5 3D BiQuad] * [https://community.elphel.com/3d+biquad/?lat=40.74257500&lng=-112.06741333&zoom=10&rating=5 3D BiQuad]  +  +==Research and Development Focus==  +=== Passive 3D Reconstruction and Long Ranging===  +* [https://blog.elphel.com/category/3d/ 3D Reconstruction and Ranging]  +=== FPGA-RTL-ASIC: Efficient Implementation of Frequency Domain Processing ===  +* [https://blog.elphel.com/category/rtl/ RTL]  +=== Calibration for Aberration Correction ===  +* [https://blog.elphel.com/category/calibration/ Calibration]  +  +     ==Development blog== ==Development blog== Andrey.filippov

‎Products

← Older revision Revision as of 05:09, 19 June 2018 (7 intermediate revisions by the same user not shown)Line 1: Line 1: −==Links==+==Presentation== −[https://blog.elphel.com/2018/05/capturing-aircraft-position-with-the-long-range-quad-stereo-camera/ Capturing Aircraft Position with the Long Range Quad Stereo Camera]+* [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf High Resolution Wide FoV CNN System for Target Classification, Ranging and Tracking (pdf)]  +   +==3D models demo and image sets==  +* [https://community.elphel.com/3d+biquad/?lat=40.74257500&lng=-112.06741333&zoom=10&rating=5 3D BiQuad]  +   +==Development blog==  +* [https://blog.elphel.com/2018/05/capturing-aircraft-position-with-the-long-range-quad-stereo-camera/ <font size='2'>'''2018/05/06'''</font> Capturing Aircraft Position with the Long Range Quad Stereo Camera]  +* [https://blog.elphel.com/2018/03/dual-quad-camera-rig-for-capturing-image-sets/ <font size='2'>'''2018/03/20'''</font> Dual Quad-Camera Rig for Capturing Image Sets]  +* [https://blog.elphel.com/2018/02/high-resolution-multi-vew-stereo-tile-processor-and-convolutional-neural-network/ <font size='2'>'''2018/02/05'''</font> High Resolution Multi-View Stereo: Tile Processor and Convolutional Neural Network]  +* [https://blog.elphel.com/2018/01/complex-lapped-transform-bayer/ <font size='2'>'''2018/01/08'''</font> Efficient Complex Lapped Transform Implementation for the Space-Variant Frequency Domain Calculations of the Bayer Mosaic Color Images]  +   +==Products==  +* [https://www3.elphel.com/products Our multiple and single camera systems products] Oleg