YOLO v3 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.
ffede5
commit).yolov3
in repository) and convert it to Keras* format (see details in the README.md file in the official repository):
Apply
keras_to_tensorflow.py.patch<tt>: `` git apply keras_to_tensorflow.py.patch ```Metric | Value |
---|---|
Type | Detection |
GFLOPs | 65.984 |
MParams | 61.922 |
Source framework | Keras* |
Accuracy metrics obtained on COCO* validation dataset for converted model.
Metric | Value |
---|---|
mAP | 62.27% |
COCO* mAP | 67.7% |
Image, name - input_1
, 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 - input_1
, shape - 1,3,416,416
, format is B,C,H,W
where:
B
- batch sizeC
- channelH
- heightW
- widthChannel order is BGR
.
conv2d_58/BiasAdd
, shape - 1,13,13,255
. The anchor values are 116,90, 156,198, 373,326
.conv2d_66/BiasAdd
, shape - 1,26,26,255
. The anchor values are 30,61, 62,45, 59,119
.conv2d_74/BiasAdd
, shape - 1,52,52,255
. The anchor values are 10,13, 16,30, 33,23
.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_58/BiasAdd/YoloRegion
, shape - 1,255,13,13
. The anchor values are 116,90, 156,198, 373,326
.conv2d_66/BiasAdd/YoloRegion
, shape - 1,255,26,26
. The anchor values are 30,61, 62,45, 59,119
.conv2d_74/BiasAdd/YoloRegion
, shape - 1,255,52,52
. The anchor values are 10,13, 16,30, 33,23
.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: