Defining a custom class for YOLO loss

[ai_curious]

@big-bbox

1. yolov2_full_detection() is that the yolo_body OR yolo_body + yolo_head?

It is equivalent to yolo_body(). it’s the layers of the model itself, not the post processing of the model output. NOTE in the darknet code used in the Autonomous Driving exercise, the output of the model is contained in the variables feats - short for features. The final layer of activations are performed in the utility function yolo_head in this section

    box_confidence = K.sigmoid(feats[..., 4:5])
    box_xy = K.sigmoid(feats[..., :2])
    box_wh = K.exp(feats[..., 2:4])
    box_class_probs = K.softmax(feats[..., 5:])

I do that inside my loss function instead.

@big-bbox

2. How exactly did you make y_train ? and what dimension is it ?
   For one class, I expect it to be : (m,19,19,5,6) with m the batch size, 5 bounding boxes, 1 class
   If you run the “preprocess_true_boxes()” function, which is provided, you have :
   detectors_mask : (m,19,19,5,1)
   matching_true_boxes : (m,19,19,5,5)
   Did you concatenate these two together to form y_train ?

My y_train came from Berkeley Deep Drive data https://bdd-data.berkeley.edu/ that I preprocessed myself to get into YOLO input format. I used 8 anchor boxes, so it was (m,19,19,8,6)

detector_mask and matching_true_boxes are then subsets of y_train…not vice versa

@big-bbox

3. How did you provide the values for “use_anchors” (in your loss function) ?
   For 5 bounding box, is it a numpy array of shape (5,2) with float values ?

Covered in this thread… Deriving YOLO anchor boxes