YOLOv5-SVHN

CNN Model based on YOLOv5 for SVHN dataset (format 2). Especially, used YOLOv5s model.

Usage

# Download and Reshape the model
import torch
model = torch.hub.load('icns-distributed-cloud/yolov5-svhn', 'svhn').fuse().eval()
model = model.autoshape()

# Prediction
prediction = model(img, size=640)
for x1, y1, x2, y2, conf, clas in pred:
    print('box: ({}, {}), ({}, {})'.format(x1, y1, x2, y2))
    print('confidence : {}'.format(conf))
    print('class: {}'.format(int(clas)))

References

• YOLOv5
• SVHN Datasets