@@ -121,6 +121,35 @@ Suggested workflows, depending on the image folder contents:
121
121
and start drawing rectangles over the images. Masks and rectangle vertices are saved as described in [ Save Layers] ( #save-layers ) .
122
122
Note that masks can be reloaded and edited at a later stage by dropping the ` vertices.csv ` file onto the canvas.
123
123
124
+ ### Workflow flowchart
125
+
126
+ ``` mermaid
127
+ %%{init: {"flowchart": {"htmlLabels": false}} }%%
128
+ graph TD
129
+ id1[What stage of labeling?]
130
+ id2[deeplabcut.label_frames]
131
+ id3[deeplabcut.refine_labels]
132
+ id4[Add labels to, or modify in, \n `CollectedData...` layer and save that layer]
133
+ id5[Modify labels in `machinelabels` layer and save \n which will create a `CollectedData...` file]
134
+ id6[Have you refined some labels from the most recent iteration and saved already?]
135
+ id7["All extracted frames are already saved in `CollectedData...`.
136
+ 1. Hide or trash all `machinelabels` layers.
137
+ 2. Then modify in and save `CollectedData`"]
138
+ id8["
139
+ 1. hide or trash all `machinelabels` layers except for the most recent.
140
+ 2. Select most recent `machinelabels` and hit `e` to show edges.
141
+ 3. Modify only in `machinelabels` and skip frames with labels without edges shown.
142
+ 4. Save `machinelabels` layer, which will add data to `CollectedData`.
143
+ - If you need to revisit this video later, ignore `machinelabels` and work only in `CollectedData`"]
144
+
145
+ id1 -->|I need to manually label new frames \n or fix my labels|id2
146
+ id1 ---->|I need to refine outlier frames \nfrom analyzed videos|id3
147
+ id2 -->id4
148
+ id3 -->|I only have a `machinelabels...` file|id5
149
+ id3 ---->|I have both `machinelabels` and `CollectedData` files|id6
150
+ id6 -->|yes|id7
151
+ id6 ---->|no, I just extracted outliers|id8
152
+ ```
124
153
125
154
### Labeling multiple image folders
126
155
0 commit comments