617 images are divided that 466 images were included in the training data set and 151 images were included in the test data set. In data set, the traffic light (go, wait,stop) are marked on the images and the coordinates have been converted to XML format for training. These clusters in the form of XML files have been converted into TFRecord files for training of the Tensorflow library, and important parameter changes have been made for training.
item {
name: "stoplight",
id: 1,
display_name: "stoplight"
}
item {
name: "stop",
id: 2,
display_name: "stop"
}
item {
name: "wait",
id: 3,
display_name: "wait"
}
item {
name: "go",
id: 4,
display_name: "go"
}
In this model I used efficientnet _d1_coco 17 tpu-32 for object detection.
In this model I used ssd_mobilenet_v1_fpn_640x640_coco17_tpu-8 for object detection.
In this model I used ssd_mobilenet_v1_fpn_640x640_coco17_tpu-8 for object detection.