2D box pre-labeling model API
Details on request and response JSON for 2D box pre-labeling model API
Last updated
Details on request and response JSON for 2D box pre-labeling model API
Last updated
Deepen AI uses a trained model for predicting labels for boxes. We have created the API for detecting boxes in an image. The details are as follows:
Endpoint: Content-type : multipart/form-data Request JSON: { "image" : "path-to-image" } Response JSON : { "book": { "book:1": { "box": [ 29.673460125923157, 19.15963813662529, 344.7966307401657, 235.8749695122242 ], "box_score": 77.78439521789551 } }, "person": { "person:1": { "box": [ 300.2075672149658, 173.55392575263977, 56.798720359802246, 69.10856366157532 ], "box_score": 83.60002040863037 } } }
Example: curl -F image=@00001.jpg -H 'Authorization: Bearer token-goes-here' (the image should be present in the directory where the command is run or the path to the image should be given)
The following 80 classes can be predicted for boxes: person, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light, fire hydrant, stop sign, parking meter, bench, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, suitcase, frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket, bottle, wine glass, cup, fork, knife, spoon, bowl, banana, apple, sandwich, orange, broccoli, carrot, hot dog, pizza, donut, cake, chair, couch, potted plant, bed, dining table, toilet, tv, laptop, mouse, remote, keyboard, cell phone, microwave, oven, toaster, sink, refrigerator, book, clock, vase, scissors, teddy bear, hair drier, toothbrush.