YOLO v3 Tiny is a real-time object detection model implemented with Keras* from this repository and converted to TensorFlow* framework. This model was pretrained on COCO* dataset with 80 classes.
d38c3d8
commit).yolov3_tiny
in repository) and convert it to Keras* format (see details in the README.md file in the official repository):Metric | Value |
---|---|
Type | Detection |
GFLOPs | 5.582 |
MParams | 8.848 |
Source framework | Keras* |
Accuracy metrics obtained on COCO* validation dataset for converted model.
Metric | Value |
---|---|
mAP | 35.9% |
COCO* mAP | 39.7% |
Image, name - image_input
, shape - 1,416,416,3
, format is B,H,W,C
where:
B
- batch sizeH
- heightW
- widthC
- channelChannel order is RGB
. Scale value - 255.
Image, name - image_input
, shape - 1,3,416,416
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
.
conv2d_9/BiasAdd
, shape - 1,13,13,255
. The anchor values are 81,82, 135,169, 344,319
.conv2d_12/BiasAdd
, shape - 1,26,26,255
. The anchor values are 23,27, 37,58, 81,82
.For each case format is B,Cx,Cy,N*85
, where
B
- batch sizeCx
, Cy
- cell indexN
- number of detection boxes for cellDetection box has format [x
,y
,h
,w
,box_score
,class_no_1
, ..., class_no_80
], where:
x
,y
) - raw coordinates of box center, apply sigmoid function to get relative to the cell coordinatesh
,w
- raw height and width of box, apply exponential function and multiply by corresponding anchors to get absolute height and width valuesbox_score
- confidence of detection box, apply sigmoid function to get confidence in [0,1] rangeclass_no_1
,...,class_no_80
- probability distribution over the classes in logits format, apply sigmoid function and multiply by obtained confidence value to get confidence of each classconv2d_9/BiasAdd/YoloRegion
, shape - 1,255,13,13
. The anchor values are 81,82, 135,169, 344,319
.conv2d_12/BiasAdd/YoloRegion
, shape - 1,255,26,26
. The anchor values are 23,27, 37,58, 81,82
.For each case format is B,N*85,Cx,Cy
, where
B
- batch sizeN
- number of detection boxes for cellCx
, Cy
- cell indexDetection box has format [x
,y
,h
,w
,box_score
,class_no_1
, ..., class_no_80
], where:
x
,y
) - coordinates of box center relative to the cellh
,w
- raw height and width of box, apply exponential function and multiply by corresponding anchors to get absolute height and width valuesbox_score
- confidence of detection box in [0,1] rangeclass_no_1
,...,class_no_80
- probability distribution over the classes in the [0,1] range, multiply by confidence value to get confidence of each classThe original model is distributed under the following license: