You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
You might want to store the snapshot and inference results for data analysis.
117
+
118
+
To enable data collector, you can set the storage directory path in config.js:
119
+
120
+
```
121
+
config.storageDirPath = '<data-storage-dirpath>';
122
+
```
123
+
124
+
and restart BerryNet.
125
+
126
+
127
+
# Use Your Data To Train
128
+
129
+
The original instruction of retraining YOLOv2 model see [github repository of darknet](https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects)
130
+
131
+
In the current of BerryNet, TinyYolo is used instead of YOLOv2.
132
+
The major differences are:
133
+
134
+
1. Create file yolo-obj.cfg with the same content as in `tiny-yolo.cfg`
135
+
2. Download pre-trained weights of darknet reference model, `darknet.weights.12`, for the convolutional layers (6.1MB)
If you use [LabelMe](http://labelme.csail.mit.edu/Release3.0/) to annotate data, `utils/xmlTotxt.py` can help convert the xml format to the text format that darknet uses.
0 commit comments