Changes for page 5. How to segment your objects with Webilastik
Last modified by puchades on 2022/09/30 16:01
From version 49.1
edited by tomazvieira
on 2022/09/11 16:35
on 2022/09/11 16:35
Change comment:
Uploaded new attachment "image-20220911163504-5.png", version {1}
To version 53.1
edited by tomazvieira
on 2022/09/11 17:13
on 2022/09/11 17:13
Change comment:
There is no comment for this version
Summary
-
Page properties (1 modified, 0 added, 0 removed)
-
Attachments (0 modified, 2 added, 0 removed)
Details
- Page properties
-
- Content
-
... ... @@ -50,7 +50,7 @@ 50 50 === Opening a Dataset from the data-proxy === 51 51 52 52 You can also load Neuroglancer Precomputed Chunks data from the data-proxy (e.g. the [[ana-workshop-event bucket>>https://wiki.ebrains.eu/bin/view/Collabs/ana-workshop-event/Bucket]]); The URLs for this kind of data follow the following scheme: 53 -\\##precomputed:~/~/https:~/~/data-proxy.ebrains.eu/api/v1/buckets/(% style="background-color:#3498db; color:#ffffff" %)my-bucket-name(% style=" color: rgb(0, 0, 0); background-color: rgb(255, 255, 255)" %)/(% style="background-color:#9b59b6; color:#ffffff" %)path/inside/your/bucket(%%)##53 +\\##precomputed:~/~/https:~/~/data-proxy.ebrains.eu/api/v1/buckets/(% style="background-color:#3498db; color:#ffffff" %)my-bucket-name(% style="background-color:#ffffff; color:#000000" %)/(% style="background-color:#9b59b6; color:#ffffff" %)path/inside/your/bucket(%%)## 54 54 55 55 where (% style="background-color:#9b59b6; color:#ffffff" %)path/inside/your/bucket(%%) should be the path to the folder containing the dataset "info" file. 56 56 ... ... @@ -61,7 +61,7 @@ 61 61 62 62 [[image:webilastik_bucket_paths.png]] 63 63 64 -=== 64 +=== === 65 65 66 66 you would type a URL like this: 67 67 ... ... @@ -80,7 +80,6 @@ 80 80 81 81 [[image:image-20220125164557-4.png]] 82 82 83 -You can also click the 84 84 85 85 ==== A Note on Neuroglancer and 2D data ==== 86 86 ... ... @@ -137,19 +137,21 @@ 137 137 138 138 [[image:image-20220222151117-1.png]] 139 139 140 -==== 139 +==== ==== 141 141 142 142 ==== Painting Labels ==== 143 143 144 144 The status display in the "Training" applet will show "training on [datasource url]" when it's ready to start painting. 145 145 146 -Now you can start adding brush strokes. Selecta color fromthecolorpicker, checkthe"EnableBrushing"checkboxto enablebrushing(anddisablenavigation), andclickanddrag overtheimagetoadd brush strokes.Ilastikwillmapeachusedcolor toa "class", and will try tofigureoutclassforeverypixelinthe image basedonthe examplesprovidedby the brush strokes.By painting,youprovide ilastikwithsamplesofwhatapixelin that particular classshouldlooklike. The following imageshowsan examplewith2 classes: teal, representingthe "foreground"or the "cell class", and magenta, representing the"background" class.145 +Now you can start adding brush strokes. By default, webilastik will create two kinds of labels: "Background" and "Foreground". You can rename them to your liking or change their colors to something more suitable for you or your dataset. You can also add more labels if you'd like ilastik to classify the pixels of your image into more than two categories. 147 147 148 - [[image:image-20220222153157-4.png]]147 +Select one of the labels from the "Current Label" dropdown or by using the "Select Label" button, check the "Enable Brushing" checkbox to enable brushing mode (**and disable navigation**), and click and drag over the image to add brush strokes. Ilastik will map each used color to a "class", and will try to figure out a class for every pixel in the image based on the examples provided by the brush strokes. By painting, you provide ilastik with samples of what a pixel in that particular class should look like. The following image shows an example with 2 classes: magenta, representing the "foreground" and green, representing the "background" class. 149 149 149 +[[image:image-20220911162555-3.png]] 150 + 150 150 Once you have some image features selected and some brush annotation of at least 2 colors, you can check "Live Update" and ilastik will automatically use your examples to predict what classes the rest of your dataset should be, displaying the results in a "predictions" tab. 151 151 152 -[[image:image-20220 222153610-5.png]]153 +[[image:image-20220911163127-4.png]] 153 153 154 154 155 155 You can keep adding or removing brush strokes to improve your predictions. ... ... @@ -160,26 +160,34 @@ 160 160 1. Adjust the layer opacity to better view the predictions or underlying raw data; 161 161 1. Advanced users: edit the shader to render the predictions in any arbitrary way; 162 162 163 -The image below shows the "predictions" tab with an opacity set to 0. 68 using the steps described above:164 +The image below shows the "predictions" tab with an opacity set to 0.88 using the steps described above: 164 164 165 -[[image:image-202201 25172238-8.png]]166 +[[image:image-20220911163504-5.png]] 166 166 167 -You can keep adding or removing features to your model, as well as adding and removing annotations, which will automatically update the predictions tab.168 +You can keep adding or removing features to your model, as well as adding and removing annotations, which will automatically refresh the predictions tab. 168 168 169 169 === Exporting Results and Running Jobs === 170 170 171 -Once you trained your pixel classifier with the previous applets, you can apply it to other datasets or even the same dataset that was used to do the training on. 172 +Once you trained your pixel classifier with the previous applets, you can apply it to other datasets or even the same dataset that was used to do the training on. You can export your results in two ways: 172 172 173 - Todoso,select adatasourcebytyping intheURLofthedatasourceintheData SourceUrlfieldand selecta scale from the datasourceastheyappearbeneath the URL field.174 +~1. As a "Predictions Map", which is a float32 image with as many channels as the number of Label colors you've used, or; 174 174 175 - Then,configureaDataSink, i.e.,a destinationthatwillreceivethe resultsof thepixel classification. Fornow,webilastikwillonlyexporttoebrains'data-proxy buckets;Fillinthe nameof thebucketandthentheprefix (i.e.:path within the bucket) where the resultsinNeuroglancer'sprecomputed chunks format should bewrittento.176 +2. As a "Simple Segmentation", which is one 3-channel uint8 image for each of the Label colors you've used. The imag will be red where that pixel is more likely to belong to the respective Label and black everywhere else. 176 176 177 - [[image:image-20220125190311-2.png]]178 +To do so, select a data source by typing in the URL of the data source in the "Url" field of the "Input" fieldset and select a scale from the data source as they appear beneath the URL field. You can also click the "Suggestions..." button to select one of the annotated datasources. 178 178 180 +Then, configure the Output, i.e., the destination that will receive the results of the pixel classification. For now, webilastik will only export to ebrains' data-proxy buckets: 181 + 182 +1. Fill in the name of the data-proxy bucket where the results in Neuroglancer's precomputed chunks format should be written to; 183 +1. Fill in the directory path inside the bucket where the results should be saved to. This path will also contain the "info" file of the precomputed chunks format. 184 + 185 +[[image:image-20220911170735-7.png]] 186 + 187 + 179 179 Finally, click export button and eventually a new job shall be created if all the parameters were filled in correctly. 180 180 181 181 You'll be able to find your results in the data-proxy GUI, in a url that looks something like this: 182 182 183 -https:~/~/data-proxy.ebrains.eu/your-bucket-name?prefix=your/ selected/prefix192 +https:~/~/data-proxy.ebrains.eu/your-bucket-name?prefix=your/info/directory/path 184 184 185 185 [[image:image-20220125191847-3.png]]
- image-20220911165711-6.png
-
- Author
-
... ... @@ -1,0 +1,1 @@ 1 +XWiki.tomazvieira - Size
-
... ... @@ -1,0 +1,1 @@ 1 +138.8 KB - Content
- image-20220911170735-7.png
-
- Author
-
... ... @@ -1,0 +1,1 @@ 1 +XWiki.tomazvieira - Size
-
... ... @@ -1,0 +1,1 @@ 1 +138.9 KB - Content