This model is a real-time neural network for object detection that detects 20 different classes. It is made up of 9 convolutional layers and 6 max-pooling layers and is a smaller version of the more complex full YOLOv2 network.
| Model | Checksum | Download (with sample test data) | ONNX version | Opset version |
|---|---|---|---|---|
| Tiny YOLOv2 | MD5 | 58 MB | 1.0 | 1 |
| MD5 | 58 MB | 1.2 | 7 | |
| MD5 | 58 MB | 1.3 | 8 |
"YOLO9000: Better, Faster, Stronger" arXiv:1612.08242
The Tiny YOLO model was trained on the Pascal VOC dataset.
The model was converted from a Core ML version of Tiny YOLO using ONNXMLTools. The source code can be found here. The Core ML model in turn was converted from the original network implemented in Darknet (via intermediate conversion through Keras).
shape (1x3x416x416)
shape (1x125x13x13)
The output is a (125x13x13) tensor where 13x13 is the number of grid cells that the image gets divided into. Each grid cell corresponds to 125 channels, made up of the 5 bounding boxes predicted by the grid cell and the 25 data elements that describe each bounding box (5x25=125). For more information on how to derive the final bounding boxes and their corresponding confidence scores, refer to this post.
Sets of sample input and output files are provided in
- serialized protobuf TensorProtos (
.pb), which are stored in the folderstest_data_set_*/.
MIT