Documentation of output blob?
Author: samuelwhiskeyjohnsonCreated Jan 17, 2025Updated Jan 17, 2025
modelFile = "res10_300x300_ssd_iter_140000_fp16.caffemodel"
configFile = "deploy.prototxt"
net = cv2.dnn.readNetFromCaffe(configFile, modelFile)
blob = cv2.dnn.blobFromImage(frame, 1.0, (300, 300), [104, 117, 123], False, False)
net.setInput(blob)
detections = net.forward()
# detections.shape == (1, 1, 200, 7)
detections[a, b, c, d]
Is there official documentation that explains what a, b, c, d are?
For example, how would I know
detections[0, 0, 3, 2] is the 4th face's confidence level.
Source: BVLC/caffe