Open veya2ztn opened 5 years ago
Follow the instruction, I can already
For yolo2 model, we know that after run
yolo2_model = load_model(MODEL_PATH.h5) prediction = yolo2_model.predict(IMAGE_DATA)
prediction is an (?,?,?,3,num_anchors * (num_classes + 5)) tensor
prediction
so if num_anchors=1, num_class=80
num_anchors=1, num_class=80
we know the prediction's last channel is (box_x,box_y,box_w,box_h,box_confidence, )
For yolo2 (80 classes), we know is just the probabilities.
But for yolo9000, we know it is an Hierarchical Classificaiton. This is mean the output probabilities here is conditional probabilities.
P(Norfolk)=P(Norfolk|terrier)P(terrier|hunting dog)...P(animal|root)
This is why we need a tree here.
tree
I do know the last value mean in of yolo2_model : the absolutly probabilities for each catalogy
I don't know what the last value mean in of yolo9000_model, is it conditional probabilities?
Does anyone know the network output meaning for yolo9000?
Follow the instruction, I can already
For yolo2 model, we know that after run
prediction
is an (?,?,?,3,num_anchors * (num_classes + 5)) tensorso if
num_anchors=1, num_class=80
we know the )
prediction
's last channel is (box_x,box_y,box_w,box_h,box_confidence,For yolo2 (80 classes), we know is just the probabilities.
But for yolo9000, we know it is an Hierarchical Classificaiton. This is mean the output probabilities here is conditional probabilities.
P(Norfolk)=P(Norfolk|terrier)P(terrier|hunting dog)...P(animal|root)
This is why we need a
tree
here.I do know the last value mean in of yolo2_model : the absolutly probabilities for each catalogy
I don't know what the last value mean in of yolo9000_model, is it conditional probabilities?
Does anyone know the network output meaning for yolo9000?