models/seg_post_model/cellpose/gui/guihelpwindowtext.html

<qt>
    <p class="has-line-data" data-line-start="5" data-line-end="6">
        <b>Main GUI mouse controls:</b>
    </p>
    <ul>
        <li class="has-line-data" data-line-start="7" data-line-end="8">Pan = left-click + drag</li>
        <li class="has-line-data" data-line-start="8" data-line-end="9">Zoom = scroll wheel (or +/= and - buttons)</li>
        <li class="has-line-data" data-line-start="9" data-line-end="10">Full view = double left-click</li>
        <li class="has-line-data" data-line-start="10" data-line-end="11">Select mask = left-click on mask</li>
        <li class="has-line-data" data-line-start="11" data-line-end="12">Delete mask = Ctrl (or COMMAND on Mac) +
            left-click
        </li>
        <li class="has-line-data" data-line-start="11" data-line-end="12">Merge masks = Alt + left-click (will merge
            last two)
        </li>
        <li class="has-line-data" data-line-start="12" data-line-end="13">Start draw mask = right-click</li>
        <li class="has-line-data" data-line-start="13" data-line-end="15">End draw mask = right-click, or return to
            circle at beginning
        </li>
    </ul>
    <p class="has-line-data" data-line-start="15" data-line-end="16">Overlaps in masks are NOT allowed. If you
        draw a mask on top of another mask, it is cropped so that it doesn’t overlap with the old mask. Masks in 2D
        should be single strokes (single stroke is checked). If you want to draw masks in 3D (experimental), then
        you can turn this option off and draw a stroke on each plane with the cell and then press ENTER. 3D
        labelling will fill in planes that you have not labelled so that you do not have to as densely label.
    </p>
    <p class="has-line-data" data-line-start="17" data-line-end="18"> <b>!NOTE!:</b> The GUI automatically saves after
        you draw a mask in 2D but NOT after 3D mask drawing and NOT after segmentation. Save in the file menu or
        with Ctrl+S. The output file is in the same folder as the loaded image with <code>_seg.npy</code> appended.
    </p>

    <p class="has-line-data" data-line-start="19" data-line-end="20"> <b>Bulk Mask Deletion</b>
        Clicking the 'delete multiple' button will allow you to select and delete multiple masks at once.
        Masks can be deselected by clicking on them again. Once you have selected all the masks you want to delete,
        click the 'done' button to delete them.
        <br>
        <br>
        Alternatively, you can create a rectangular region to delete a regions of masks by clicking the
        'delete multiple' button, and then moving and/or resizing the region to select the masks you want to delete.
        Once you have selected the masks you want to delete, click the 'done' button to delete them.
        <br>
        <br>
        At any point in the process, you can click the 'cancel' button to cancel the bulk deletion.
    </p>
    <hr>
    <table class="table table-striped table-bordered">
        <br>
        <br>
        FYI there are tooltips throughout the GUI (hover over text to see)
        <br>
        <thead>
        <tr>
            <th>Keyboard shortcuts</th>
            <th>Description</th>
        </tr>
        </thead>
        <tbody>
        <tr>
            <td>=/+ button // - button</td>
            <td>zoom in // zoom out</td>
        </tr>
        <tr>
            <td>CTRL+Z</td>
            <td>undo previously drawn mask/stroke</td>
        </tr>
        <tr>
            <td>CTRL+Y</td>
            <td>undo remove mask</td>
        </tr>
        <tr>
            <td>CTRL+0</td>
            <td>clear all masks</td>
        </tr>
        <tr>
            <td>CTRL+L</td>
            <td>load image (can alternatively drag and drop image)</td>
        </tr>
        <tr>
            <td>CTRL+S</td>
            <td>SAVE MASKS IN IMAGE to <code>_seg.npy</code> file</td>
        </tr>
        <tr>
            <td>CTRL+T</td>
            <td>train model using _seg.npy files in folder
        </tr>
        <tr>
            <td>CTRL+P</td>
            <td>load <code>_seg.npy</code> file (note: it will load automatically with image if it exists)</td>
        </tr>
        <tr>
            <td>CTRL+M</td>
            <td>load masks file (must be same size as image with 0 for NO mask, and 1,2,3… for masks)</td>
        </tr>
        <tr>
            <td>CTRL+N</td>
            <td>save masks as PNG</td>
        </tr>
        <tr>
            <td>CTRL+R</td>
            <td>save ROIs to native ImageJ ROI format</td>
        </tr>
        <tr>
            <td>CTRL+F</td>
            <td>save flows to image file</td>
        </tr>
        <tr>
            <td>A/D or LEFT/RIGHT</td>
            <td>cycle through images in current directory</td>
        </tr>
        <tr>
            <td>W/S or UP/DOWN</td>
            <td>change color (RGB/gray/red/green/blue)</td>
        </tr>
        <tr>
            <td>R / G / B</td>
            <td>toggle between RGB and Red or Green or Blue</td>
        </tr>
        <tr>
            <td>PAGE-UP / PAGE-DOWN</td>
            <td>change to flows and cell prob views (if segmentation computed)</td>
        </tr>
        <tr>
            <td>X</td>
            <td>turn masks ON or OFF</td>
        </tr>
        <tr>
            <td>Z</td>
            <td>toggle outlines ON or OFF</td>
        </tr>
        <tr>
            <td>, / .</td>
            <td>increase / decrease brush size for drawing masks</td>
        </tr>
        </tbody>
    </table>
    <p class="has-line-data" data-line-start="36" data-line-end="37"><strong>Segmentation options 
        (2D only) </strong></p>
    <p class="has-line-data" data-line-start="38" data-line-end="39">use GPU: if you have specially 
        installed the cuda version of torch, then you can activate this. Due to the size of the 
        transformer network, it will greatly speed up the processing time.</p>
    <p class="has-line-data" data-line-start="40" data-line-end="41">There are no channel options
        in v4.0.1+ since all 3 channels are used for segmentation. </p>
</qt>