Imaging solutions with Free Software & Open Hardware

Who's online

There are currently 0 users online.

Subscribe to Wiki Recent Changes feed
Track the most recent changes to the wiki in this feed. MediaWiki 1.28.0
Updated: 19 sec ago

Tiff file format for pre-processed quad-stereo sets

Thu, 07/12/2018 - 18:49

‎Python

← Older revision Revision as of 00:49, 13 July 2018 Line 110: Line 110:    values data: (242, 324, 3)</font>   values data: (242, 324, 3)</font>    −[[File:Ml tiff stack python tile packing.jpeg|thumb|400px|Fig.4 Single layer packing]]+[[File:Ml tiff stack python tile packing.jpeg|thumb|400px|Fig.4 Single layer packing (actually, see the CVPR2018 presentation, p.23)]]  '''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to: '''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  * <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font> * <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font> Oleg

Tiff file format for pre-processed quad-stereo sets

Thu, 07/12/2018 - 18:49

‎Python

← Older revision Revision as of 00:49, 13 July 2018 (One intermediate revision by the same user not shown)Line 110: Line 110:    values data: (242, 324, 3)</font>   values data: (242, 324, 3)</font>    − +[[File:Ml tiff stack python tile packing.jpeg|thumb|400px|Fig.4 Single layer packing (actually, see the CVPR2018 presentation, p.23)]]  '''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to: '''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  * <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font> * <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font> Oleg

Tiff file format for pre-processed quad-stereo sets

Thu, 07/12/2018 - 14:20

‎Python

← Older revision Revision as of 20:20, 12 July 2018 Line 110: Line 110:    values data: (242, 324, 3)</font>   values data: (242, 324, 3)</font>    − +[[File:Ml tiff stack python tile packing.jpeg|thumb|400px|Fig.4 Single layer packing]]  '''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to: '''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  * <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font> * <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font> Oleg

File:Ml tiff stack python tile packing.jpeg

Thu, 07/12/2018 - 14:20

Oleg uploaded File:Ml tiff stack python tile packing.jpeg

New page

== Licensing ==
{{CC }} Oleg

File:Ml tiff stack python values.jpeg

Thu, 07/12/2018 - 14:13

Oleg uploaded a new version of File:Ml tiff stack python values.jpeg

New page

== Licensing ==
{{CC }} Oleg

Tiff file format for pre-processed quad-stereo sets

Thu, 07/12/2018 - 14:08

← Older revision Revision as of 20:08, 12 July 2018 (2 intermediate revisions by the same user not shown)Line 60: Line 60:  ImageJ - it has a native support for stacks, each stack has a name label stored (along with related xml info) in the ImageJ tiff tags. To read tiff tags in ImageJ, go '''Image > Show Info...''' ImageJ - it has a native support for stacks, each stack has a name label stored (along with related xml info) in the ImageJ tiff tags. To read tiff tags in ImageJ, go '''Image > Show Info...'''  ====Python==== ====Python==== −Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:+'''1.''' Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  * <font color='DarkGreen'>'''Get tiff tags values (Pillow)'''</font> * <font color='DarkGreen'>'''Get tiff tags values (Pillow)'''</font>  * <font color='DarkGreen'>'''Parse Properties xml data stored by ImageJ in the tiff tags'''</font> * <font color='DarkGreen'>'''Parse Properties xml data stored by ImageJ in the tiff tags'''</font> Line 109: Line 109:    image data:  (242, 324, 9, 9, 4)   image data:  (242, 324, 9, 9, 4)    values data: (242, 324, 3)</font>   values data: (242, 324, 3)</font>  +  +  +'''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  +* <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font>  + <font size=2>'''# The current packing is hardcoded in the script: (TY,TX,9,9,4) -> (TY,TX,100)'''  + # Get tiles from a tiff stack  + import pack_tile as pile  + packed_tiles = pile.pack(tile)  + # packed_tiles get stacked with '''estimated disparity''' (see '''test_nn_feed.py''')  + packed_tiles = np.dstack((packed_tiles,values[:,:,0])) Oleg

Tiff file format for pre-processed quad-stereo sets

Thu, 07/12/2018 - 14:08

← Older revision Revision as of 20:08, 12 July 2018 (4 intermediate revisions by the same user not shown)Line 47: Line 47:  [[File:Ml tiff stack imagej.jpeg|thumb|400px|Fig.1 Opened in ImageJ]] [[File:Ml tiff stack imagej.jpeg|thumb|400px|Fig.1 Opened in ImageJ]]  [[File:Ml tiff stack python values.jpeg|thumb|800px|Fig.2 Decoded 'value'-layers]] [[File:Ml tiff stack python values.jpeg|thumb|800px|Fig.2 Decoded 'value'-layers]]  +[[File:Ml tiff stack python data layers.jpeg|thumb|500px|Fig.3 Data layers]]  * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]: * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]:  ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] Line 59: Line 60:  ImageJ - it has a native support for stacks, each stack has a name label stored (along with related xml info) in the ImageJ tiff tags. To read tiff tags in ImageJ, go '''Image > Show Info...''' ImageJ - it has a native support for stacks, each stack has a name label stored (along with related xml info) in the ImageJ tiff tags. To read tiff tags in ImageJ, go '''Image > Show Info...'''  ====Python==== ====Python==== −Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:+'''1.''' Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  * <font color='DarkGreen'>'''Get tiff tags values (Pillow)'''</font> * <font color='DarkGreen'>'''Get tiff tags values (Pillow)'''</font>  * <font color='DarkGreen'>'''Parse Properties xml data stored by ImageJ in the tiff tags'''</font> * <font color='DarkGreen'>'''Parse Properties xml data stored by ImageJ in the tiff tags'''</font> Line 104: Line 105:       −Upon opening tiff the image shape will be '''(height,width,layer)''' - for further processing it needs to be reshaped to '''(height_in_tiles, width_in_tiles, tile_height, tile_width, layer)''', example:+Upon opening tiff the image will be a numpy array of shape '''(height,width,layer)''' - for further processing it is reshaped to '''(height_in_tiles, width_in_tiles, tile_height, tile_width, layer)''', example:    <font size='2'>tiff stack shape: (2178, 2916, 5)   <font size='2'>tiff stack shape: (2178, 2916, 5)    image data:  (242, 324, 9, 9, 4)   image data:  (242, 324, 9, 9, 4)    values data: (242, 324, 3)</font>   values data: (242, 324, 3)</font>  +  +  +'''2.''' Use '''pack_tile.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  +* <font color='DarkGreen'>'''Pack image tiles for better structuring for ML'''</font>  + <font size=2>'''# The current packing is hardcoded in the script: (TY,TX,9,9,4) -> (TY,TX,100)'''  + # Get tiles from a tiff stack  + import pack_tile as pile  + packed_tiles = pile.pack(tile)  + # packed_tiles get stacked with '''estimated disparity''' (see '''test_nn_feed.py''')  + packed_tiles = np.dstack((packed_tiles,values[:,:,0])) Oleg

Tiff file format for pre-processed quad-stereo sets

Wed, 07/11/2018 - 17:19

← Older revision Revision as of 23:19, 11 July 2018 (One intermediate revision by the same user not shown)Line 47: Line 47:  [[File:Ml tiff stack imagej.jpeg|thumb|400px|Fig.1 Opened in ImageJ]] [[File:Ml tiff stack imagej.jpeg|thumb|400px|Fig.1 Opened in ImageJ]]  [[File:Ml tiff stack python values.jpeg|thumb|800px|Fig.2 Decoded 'value'-layers]] [[File:Ml tiff stack python values.jpeg|thumb|800px|Fig.2 Decoded 'value'-layers]]  +[[File:Ml tiff stack python data layers.jpeg|thumb|500px|Fig.3 Data layers]]  * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]: * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]:  ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] Line 104: Line 105:       −Upon opening tiff the image shape will be '''(height,width,layer)''' - for further processing it needs to be reshaped to '''(height_in_tiles, width_in_tiles, tile_height, tile_width, layer)''', example:+Upon opening tiff the image will be a numpy array of shape '''(height,width,layer)''' - for further processing it is reshaped to '''(height_in_tiles, width_in_tiles, tile_height, tile_width, layer)''', example:    <font size='2'>tiff stack shape: (2178, 2916, 5)   <font size='2'>tiff stack shape: (2178, 2916, 5)    image data:  (242, 324, 9, 9, 4)   image data:  (242, 324, 9, 9, 4)    values data: (242, 324, 3)</font>   values data: (242, 324, 3)</font> Oleg

Tiff file format for pre-processed quad-stereo sets

Wed, 07/11/2018 - 16:50

‎TIFF stacks for ML

← Older revision Revision as of 22:50, 11 July 2018 Line 47: Line 47:  [[File:Ml tiff stack imagej.jpeg|thumb|400px|Fig.1 Opened in ImageJ]] [[File:Ml tiff stack imagej.jpeg|thumb|400px|Fig.1 Opened in ImageJ]]  [[File:Ml tiff stack python values.jpeg|thumb|800px|Fig.2 Decoded 'value'-layers]] [[File:Ml tiff stack python values.jpeg|thumb|800px|Fig.2 Decoded 'value'-layers]]  +[[File:Ml tiff stack python data layers.jpeg|thumb|500px|Fig.3 Data layers]]  * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]: * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]:  ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] Oleg

File:Ml tiff stack python data layers.jpeg

Wed, 07/11/2018 - 16:49

Oleg uploaded File:Ml tiff stack python data layers.jpeg

New page

== Licensing ==
{{CC }} Oleg

Tiff file format for pre-processed quad-stereo sets

Wed, 07/11/2018 - 16:44

‎Python

← Older revision Revision as of 22:44, 11 July 2018 (4 intermediate revisions by the same user not shown)Line 45: Line 45:     ==<font color='ForestGreen'>TIFF stacks for ML</font>== ==<font color='ForestGreen'>TIFF stacks for ML</font>==  +[[File:Ml tiff stack imagej.jpeg|thumb|400px|Fig.1 Opened in ImageJ]]  +[[File:Ml tiff stack python values.jpeg|thumb|800px|Fig.2 Decoded 'value'-layers]]  * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]: * What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]:  ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] ** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other'''] Line 58: Line 60:  ====Python==== ====Python====  Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to: Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to: −* get tiff tags values (Pillow)+* <font color='DarkGreen'>'''Get tiff tags values (Pillow)'''</font> −* parse Properties xml data stored in the tiff tags used by ImageJ+* <font color='DarkGreen'>'''Parse Properties xml data stored by ImageJ in the tiff tags'''</font> −* get tile dimensions from Properties+* <font color='DarkGreen'>'''Get tiles dimensions from Properties'''</font> −* read layers as numpy arrays for further computations or plotting+* <font color='DarkGreen'>'''Convert layers to numpy arrays (split into tiles or optionally not split) for further computations and plotting'''</font> −Example:+Example (more examples are commented out in the __main__ section of the script):    <font size='1' style='line-height:0.5;'>'''~$ python3 imagej_tiff.py 1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS0.00000.tiff'''   <font size='1' style='line-height:0.5;'>'''~$ python3 imagej_tiff.py 1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS0.00000.tiff'''    time: 1531344391.7055812   time: 1531344391.7055812 Oleg

File:Ml tiff stack python values.jpeg

Wed, 07/11/2018 - 16:20

Oleg uploaded File:Ml tiff stack python values.jpeg

New page

== Licensing ==
{{CC }} Oleg

File:Ml tiff stack imagej.jpeg

Wed, 07/11/2018 - 16:19

Oleg uploaded File:Ml tiff stack imagej.jpeg

New page

== Licensing ==
{{CC }} Oleg

Tiff file format for pre-processed quad-stereo sets

Wed, 07/11/2018 - 15:48

‎TIFF stacks for ML

← Older revision Revision as of 21:48, 11 July 2018 (15 intermediate revisions by the same user not shown)Line 3: Line 3:    <font size='2'>'''1527256903_350165/'''   <font size='2'>'''1527256903_350165/'''    ├── 1527256903_350165.kml   ├── 1527256903_350165.kml −  ├── '''jp4'''+  ├── '''jp4''' (source files directory)    │  ├── <font color='RoyalBlue'>1527256903_350165_0.jp4</font>   │  ├── <font color='RoyalBlue'>1527256903_350165_0.jp4</font>    │  ├── <font color='RoyalBlue'>...</font>   │  ├── <font color='RoyalBlue'>...</font> Line 12: Line 12:    ├── rating.txt   ├── rating.txt    ├── thumb.jpeg   ├── thumb.jpeg −  └── '''v03'''+  └── '''v03''' (model version)       ├── <font color='Indigo'>1527256903_350165-00-D0.0.jpeg</font>      ├── <font color='Indigo'>1527256903_350165-00-D0.0.jpeg</font>       ├── <font color='Indigo'>...</font>      ├── <font color='Indigo'>...</font> Line 26: Line 26:       ├── <font color='DarkGoldenrod'>1527256903_350165.obj</font>      ├── <font color='DarkGoldenrod'>1527256903_350165.obj</font>       ├── <font color='DarkGoldenrod'>1527256903_350165.x3d</font>      ├── <font color='DarkGoldenrod'>1527256903_350165.x3d</font> −     └── '''ml'''+     └── '''ml''' (directory with processed data files for ML)           ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-2.00000.tiff</font>          ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-2.00000.tiff</font>           ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-1.00000.tiff</font>          ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-1.00000.tiff</font> Line 34: Line 34:  where: where:  * <font color='RoyalBlue'>'''*.jp4'''</font> - source files, 0..3 - quad stereo camera #1, 4..7 - quad stereo camera #2, and so on if there are more cameras in the system. * <font color='RoyalBlue'>'''*.jp4'''</font> - source files, 0..3 - quad stereo camera #1, 4..7 - quad stereo camera #2, and so on if there are more cameras in the system. −* <font color='Indigo'>'''*-D0.0.jpeg'''</font> - disparity = 0, images are undistorted to a common polynom+* <font color='Indigo'>'''*-D0.0.jpeg'''</font> - disparity = 0, images are undistorted to a distortion polynom common for each image  * <font color='OrangeRed'>'''*.corr-xml'''</font> - ImageJ plugin's settings file? * <font color='OrangeRed'>'''*.corr-xml'''</font> - ImageJ plugin's settings file?  * <font color='Maroon'>'''*-DSI_COMBO.tiff'''</font> - Disparity Space Image - tiff stack * <font color='Maroon'>'''*-DSI_COMBO.tiff'''</font> - Disparity Space Image - tiff stack Line 40: Line 40:  * <font color='DarkGoldenrod'>'''*.x3d, *.png'''</font> - X3D format model with textures. The textures are shared with the OBJ format model * <font color='DarkGoldenrod'>'''*.x3d, *.png'''</font> - X3D format model with textures. The textures are shared with the OBJ format model  * <font color='DarkGoldenrod'>'''*.obj, *.mtl, *.png'''</font> - OBJ format model with textures * <font color='DarkGoldenrod'>'''*.obj, *.mtl, *.png'''</font> - OBJ format model with textures −* <font color='ForestGreen'>'''ml/*.tiff'''</font> - TIFF stack of pre-processed images for ML+* <font color='ForestGreen'>'''*.tiff'''</font> - TIFF stack of pre-processed images for ML     * *.kml, rating.txt, thumb.jpeg - files, related to the online viewer only * *.kml, rating.txt, thumb.jpeg - files, related to the online viewer only    −==Stacked TIFF==+==<font color='ForestGreen'>TIFF stacks for ML</font>== − +* What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]:  +** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other''']  +*** '''diagm-pair'''  +*** '''diago-pair'''  +*** '''hor-pairs'''  +*** '''vert-pairs'''  +*** '''other''' - encoded values: estimated disparity, residual disparity and confidence for the residual disparity  * The source files are processed using a plugin for ImageJ, the output file for each set is a tiff stack * The source files are processed using a plugin for ImageJ, the output file for each set is a tiff stack  * There are a few ways to view the stack: * There are a few ways to view the stack: −** just open with ImageJ+====ImageJ====  +ImageJ - it has a native support for stacks, each stack has a name label stored (along with related xml info) in the ImageJ tiff tags. To read tiff tags in ImageJ, go '''Image > Show Info...'''  +====Python====  +Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff] to:  +* get tiff tags values (Pillow)  +* parse Properties xml data stored in the tiff tags used by ImageJ  +* get tile dimensions from Properties  +* read layers as numpy arrays for further computations or plotting  +Example:  + <font size='1' style='line-height:0.5;'>'''~$ python3 imagej_tiff.py 1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS0.00000.tiff'''  + time: 1531344391.7055812  + time: 1531344392.5336654  + TIFF stack labels: ['diagm-pair', 'diago-pair', 'hor-pairs', 'vert-pairs', 'other']  + <?xml version="1.0" ?>  + <properties>  +        <ML_OTHER_TARGET>0</ML_OTHER_TARGET>  +        <tileWidth>9</tileWidth>  +        <disparityRadiusMain>257.22231560274076</disparityRadiusMain>  +        <comment_ML_OTHER_GTRUTH_STRENGTH>Offset of the ground truth strength in the &quot;other&quot; layer tile</comment_ML_OTHER_GTRUTH_STRENGTH>  +        <data_min>-0.16894744988183344</data_min>  +        <comment_intercameraBaseline>Horizontal distance between the main and the auxiliary camera centers (mm). Disparity is specified for the main camera</comment_intercameraBaseline>  +        <ML_OTHER_GTRUTH>2</ML_OTHER_GTRUTH>  +        <data_max>0.6260986600450271</data_max>  +        <disparityRadiusAux>151.5308819757923</disparityRadiusAux>  +        <comment_disparityRadiusAux>Side of the square where 4 main camera subcameras are located (mm). Disparity is specified for the main camera</comment_disparityRadiusAux>  +        <comment_disparityRadiusMain>Side of the square where 4 main camera subcameras are located (mm)</comment_disparityRadiusMain>  +        <comment_dispOffset>Tile target disparity minum ground truth disparity</comment_dispOffset>  +        <comment_tileWidth>Square tile size for each 2d correlation, always odd</comment_tileWidth>  +        <comment_data_min>Defined only for 8bpp mode - value, corresponding to -127 (-128 is NaN)</comment_data_min>  +        <comment_data_max>Defined only for 8bpp mode - value, corresponding to +127 (-128 is NaN)</comment_data_max>  +        <comment_ML_OTHER_TARGET>Offset of the target disparity in the &quot;other&quot; layer tile</comment_ML_OTHER_TARGET>  +        <VERSION>1.0</VERSION>  +        <dispOffset>0.0</dispOffset>  +        <comment_ML_OTHER_GTRUTH>Offset of the ground truth disparity in the &quot;other&quot; layer tile</comment_ML_OTHER_GTRUTH>  +        <ML_OTHER_GTRUTH_STRENGTH>4</ML_OTHER_GTRUTH_STRENGTH>  +        <intercameraBaseline>1256.0</intercameraBaseline>  + </properties>  + Tiles shape: 9x9  + Data min: -0.16894744988183344  + Data max: 0.6260986600450271  + (2178, 2916, 5)  + Stack of images shape: (242, 324, 9, 9, 4)  + time: 1531344392.7290232  + Stack of values shape: (242, 324, 3)  + time: 1531344393.5556033</font>  +   +   +   +Upon opening tiff the image shape will be '''(height,width,layer)''' - for further processing it needs to be reshaped to '''(height_in_tiles, width_in_tiles, tile_height, tile_width, layer)''', example:  + <font size='2'>tiff stack shape: (2178, 2916, 5)  + image data:  (242, 324, 9, 9, 4)  + values data: (242, 324, 3)</font> Oleg

Tiff file format for pre-processed quad-stereo sets

Wed, 07/11/2018 - 14:42

‎TIFF stacks for ML

← Older revision Revision as of 20:42, 11 July 2018 (12 intermediate revisions by the same user not shown)Line 3: Line 3:    <font size='2'>'''1527256903_350165/'''   <font size='2'>'''1527256903_350165/'''    ├── 1527256903_350165.kml   ├── 1527256903_350165.kml −  ├── '''jp4'''+  ├── '''jp4''' (source files directory)    │  ├── <font color='RoyalBlue'>1527256903_350165_0.jp4</font>   │  ├── <font color='RoyalBlue'>1527256903_350165_0.jp4</font>    │  ├── <font color='RoyalBlue'>...</font>   │  ├── <font color='RoyalBlue'>...</font> Line 12: Line 12:    ├── rating.txt   ├── rating.txt    ├── thumb.jpeg   ├── thumb.jpeg −  └── '''v03'''+  └── '''v03''' (model version)       ├── <font color='Indigo'>1527256903_350165-00-D0.0.jpeg</font>      ├── <font color='Indigo'>1527256903_350165-00-D0.0.jpeg</font>       ├── <font color='Indigo'>...</font>      ├── <font color='Indigo'>...</font> Line 26: Line 26:       ├── <font color='DarkGoldenrod'>1527256903_350165.obj</font>      ├── <font color='DarkGoldenrod'>1527256903_350165.obj</font>       ├── <font color='DarkGoldenrod'>1527256903_350165.x3d</font>      ├── <font color='DarkGoldenrod'>1527256903_350165.x3d</font> −     └── '''ml'''+     └── '''ml''' (directory with processed data files for ML)           ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-2.00000.tiff</font>          ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-2.00000.tiff</font>           ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-1.00000.tiff</font>          ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-1.00000.tiff</font> Line 34: Line 34:  where: where:  * <font color='RoyalBlue'>'''*.jp4'''</font> - source files, 0..3 - quad stereo camera #1, 4..7 - quad stereo camera #2, and so on if there are more cameras in the system. * <font color='RoyalBlue'>'''*.jp4'''</font> - source files, 0..3 - quad stereo camera #1, 4..7 - quad stereo camera #2, and so on if there are more cameras in the system. −* <font color='Indigo'>'''*-D0.0.jpeg'''</font> - disparity = 0, images are undistorted to a common polynom+* <font color='Indigo'>'''*-D0.0.jpeg'''</font> - disparity = 0, images are undistorted to a distortion polynom common for each image  * <font color='OrangeRed'>'''*.corr-xml'''</font> - ImageJ plugin's settings file? * <font color='OrangeRed'>'''*.corr-xml'''</font> - ImageJ plugin's settings file?  * <font color='Maroon'>'''*-DSI_COMBO.tiff'''</font> - Disparity Space Image - tiff stack * <font color='Maroon'>'''*-DSI_COMBO.tiff'''</font> - Disparity Space Image - tiff stack Line 40: Line 40:  * <font color='DarkGoldenrod'>'''*.x3d, *.png'''</font> - X3D format model with textures. The textures are shared with the OBJ format model * <font color='DarkGoldenrod'>'''*.x3d, *.png'''</font> - X3D format model with textures. The textures are shared with the OBJ format model  * <font color='DarkGoldenrod'>'''*.obj, *.mtl, *.png'''</font> - OBJ format model with textures * <font color='DarkGoldenrod'>'''*.obj, *.mtl, *.png'''</font> - OBJ format model with textures −* <font color='ForestGreen'>'''ml/*.tiff'''</font> - TIFF stack of pre-processed images for ML+* <font color='ForestGreen'>'''*.tiff'''</font> - TIFF stack of pre-processed images for ML     * *.kml, rating.txt, thumb.jpeg - files, related to the online viewer only * *.kml, rating.txt, thumb.jpeg - files, related to the online viewer only    −==Stacked TIFF==+==<font color='ForestGreen'>TIFF stacks for ML</font>== − +* What's in each stack is described in the [https://community.elphel.com/files/presentations/Elphel_TP-CNN_slides.pdf presentation for CVPR2018, pp.19-21]:  +** 5 layers in the stack: ['''diagm-pair''', '''diago-pair''', '''hor-pairs''', '''vert-pairs''', '''other''']  +*** '''diagm-pair'''  +*** '''diago-pair'''  +*** '''hor-pairs'''  +*** '''vert-pairs'''  +*** '''other''' - encoded values: image disparity, estimated disparity and confidence for the estimated disparity  * The source files are processed using a plugin for ImageJ, the output file for each set is a tiff stack * The source files are processed using a plugin for ImageJ, the output file for each set is a tiff stack  * There are a few ways to view the stack: * There are a few ways to view the stack: −** just open with ImageJ+** Open with ImageJ - it has a native support for stacks, each stack has a name label stored (along with related xml info) in the ImageJ tiff tags. To read tiff tags in ImageJ, go '''Image > Show Info...'''  +** Use '''imagej_tiff.py''' from [https://git.elphel.com/Elphel/python3-imagej-tiff python3-imagej-tiff]  +*** Upon opening tiff the image shape will be '''(height,width,layer)''' - for further processing it needs to be reshaped to '''(height_in_tiles, width_in_tiles, tile_height, tile_width, layer)''':  + <font size='2'>tiff stack shape: (2178, 2916, 5)  + image data:  (242, 324, 9, 9, 4)  + values data: (242, 324, 3)</font> Oleg

Tiff file format for pre-processed quad-stereo sets

Wed, 07/11/2018 - 13:39

← Older revision Revision as of 19:39, 11 July 2018 (4 intermediate revisions by the same user not shown)Line 3: Line 3:    <font size='2'>'''1527256903_350165/'''   <font size='2'>'''1527256903_350165/'''    ├── 1527256903_350165.kml   ├── 1527256903_350165.kml −  ├── '''jp4'''+  ├── '''jp4''' (source files directory)    │  ├── <font color='RoyalBlue'>1527256903_350165_0.jp4</font>   │  ├── <font color='RoyalBlue'>1527256903_350165_0.jp4</font>    │  ├── <font color='RoyalBlue'>...</font>   │  ├── <font color='RoyalBlue'>...</font> Line 12: Line 12:    ├── rating.txt   ├── rating.txt    ├── thumb.jpeg   ├── thumb.jpeg −  └── '''v03'''+  └── '''v03''' (model version)       ├── <font color='Indigo'>1527256903_350165-00-D0.0.jpeg</font>      ├── <font color='Indigo'>1527256903_350165-00-D0.0.jpeg</font>       ├── <font color='Indigo'>...</font>      ├── <font color='Indigo'>...</font> Line 26: Line 26:       ├── <font color='DarkGoldenrod'>1527256903_350165.obj</font>      ├── <font color='DarkGoldenrod'>1527256903_350165.obj</font>       ├── <font color='DarkGoldenrod'>1527256903_350165.x3d</font>      ├── <font color='DarkGoldenrod'>1527256903_350165.x3d</font> −     └── '''ml'''+     └── '''ml''' (directory with processed data files for ML)           ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-2.00000.tiff</font>          ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-2.00000.tiff</font>           ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-1.00000.tiff</font>          ├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-1.00000.tiff</font> Line 34: Line 34:  where: where:  * <font color='RoyalBlue'>'''*.jp4'''</font> - source files, 0..3 - quad stereo camera #1, 4..7 - quad stereo camera #2, and so on if there are more cameras in the system. * <font color='RoyalBlue'>'''*.jp4'''</font> - source files, 0..3 - quad stereo camera #1, 4..7 - quad stereo camera #2, and so on if there are more cameras in the system. −* <font color='Indigo'>'''*-D0.0.jpeg'''</font> - disparity = 0, images are undistorted to a common polynom+* <font color='Indigo'>'''*-D0.0.jpeg'''</font> - disparity = 0, images are undistorted to a distortion polynom common for each image  * <font color='OrangeRed'>'''*.corr-xml'''</font> - ImageJ plugin's settings file? * <font color='OrangeRed'>'''*.corr-xml'''</font> - ImageJ plugin's settings file?  * <font color='Maroon'>'''*-DSI_COMBO.tiff'''</font> - Disparity Space Image - tiff stack * <font color='Maroon'>'''*-DSI_COMBO.tiff'''</font> - Disparity Space Image - tiff stack Line 40: Line 40:  * <font color='DarkGoldenrod'>'''*.x3d, *.png'''</font> - X3D format model with textures. The textures are shared with the OBJ format model * <font color='DarkGoldenrod'>'''*.x3d, *.png'''</font> - X3D format model with textures. The textures are shared with the OBJ format model  * <font color='DarkGoldenrod'>'''*.obj, *.mtl, *.png'''</font> - OBJ format model with textures * <font color='DarkGoldenrod'>'''*.obj, *.mtl, *.png'''</font> - OBJ format model with textures −* <font color='ForestGreen'>'''ml/*.tiff'''</font> - TIFF stack of pre-processed images for ML+* <font color='ForestGreen'>'''*.tiff'''</font> - TIFF stack of pre-processed images for ML     * *.kml, rating.txt, thumb.jpeg - files, related to the online viewer only * *.kml, rating.txt, thumb.jpeg - files, related to the online viewer only    −==Stacked TIFF==+==<font color='ForestGreen'>TIFF stacks for ML</font>==     * The source files are processed using a plugin for ImageJ, the output file for each set is a tiff stack * The source files are processed using a plugin for ImageJ, the output file for each set is a tiff stack  * There are a few ways to view the stack: * There are a few ways to view the stack:  ** just open with ImageJ ** just open with ImageJ Oleg

Tiff file format for pre-processed quad-stereo sets

Wed, 07/11/2018 - 13:08

Created page with "==Image sets== Example tree of a single set: <font size='2'>'''1527256903_350165/''' ├── 1527256903_350165.kml ├── '''jp4''' │ ├── <font color='Royal..."

New page

==Image sets==
Example tree of a single set:
<font size='2'>'''1527256903_350165/'''
├── 1527256903_350165.kml
├── '''jp4'''
│ ├── <font color='RoyalBlue'>1527256903_350165_0.jp4</font>
│ ├── <font color='RoyalBlue'>...</font>
│ ├── <font color='RoyalBlue'>1527256903_350165_3.jp4</font>
│ ├── <font color='RoyalBlue'>1527256903_350165_4.jp4</font>
│ ├── <font color='RoyalBlue'>...</font>
│ └── <font color='RoyalBlue'>1527256903_350165_7.jp4</font>
├── rating.txt
├── thumb.jpeg
└── '''v03'''
├── <font color='Indigo'>1527256903_350165-00-D0.0.jpeg</font>
├── <font color='Indigo'>...</font>
├── <font color='Indigo'>1527256903_350165-07-D0.0.jpeg</font>
├── <font color='OrangeRed'>1527256903_350165.corr-xml</font>
├── <font color='Maroon'>1527256903_350165-DSI_COMBO.tiff</font>
├── <font color='DarkSlateGray'>1527256903_350165-EXTRINSICS.corr-xml</font>
├── <font color='DarkGoldenrod'>1527256903_350165-img1-texture.png</font>
├── <font color='DarkGoldenrod'>...</font>
├── <font color='DarkGoldenrod'>1527256903_350165-img2001-texture.png</font>
├── <font color='DarkGoldenrod'>1527256903_350165-img_infinity-texture.png</font>
├── <font color='DarkGoldenrod'>1527256903_350165.mtl</font>
├── <font color='DarkGoldenrod'>1527256903_350165.obj</font>
├── <font color='DarkGoldenrod'>1527256903_350165.x3d</font>
└── '''ml'''
├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-2.00000.tiff</font>
├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS-1.00000.tiff</font>
├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS0.00000.tiff</font>
├── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS1.00000.tiff</font>
└── <font color='ForestGreen'>1527256903_350165-ML_DATA-08B-O-FZ0.05-OFFS2.00000.tiff</font></font>
where:
* <font color='RoyalBlue'>'''*.jp4'''</font> - source files, 0..3 - quad stereo camera #1, 4..7 - quad stereo camera #2, and so on if there are more cameras in the system.
* <font color='Indigo'>'''*-D0.0.jpeg'''</font> - disparity = 0, images are undistorted to a common polynom
* <font color='OrangeRed'>'''*.corr-xml'''</font> - ImageJ plugin's settings file?
* <font color='Maroon'>'''*-DSI_COMBO.tiff'''</font> - Disparity Space Image - tiff stack
* <font color='DarkSlateGray'>'''*-EXTRINSICS.corr-xml'''</font> - extrinsic parameters of the multicamera system
* <font color='DarkGoldenrod'>'''*.x3d, *.png'''</font> - X3D format model with textures. The textures are shared with the OBJ format model
* <font color='DarkGoldenrod'>'''*.obj, *.mtl, *.png'''</font> - OBJ format model with textures
* <font color='ForestGreen'>'''ml/*.tiff'''</font> - TIFF stack of pre-processed images for ML

* *.kml, rating.txt, thumb.jpeg - files, related to the online viewer only

==Stacked TIFF==

* The source files are processed using a plugin for ImageJ, the output file for each set is a tiff stack
* There are a few ways to view the stack:
** just open with ImageJ Oleg

Tensorflow with gpu

Fri, 07/06/2018 - 11:07

‎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

Poky manual

Tue, 06/26/2018 - 12:25

‎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

FPGA bitstream versions

Tue, 06/26/2018 - 11:19

‎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

Pages