i'm trying to extract the features vector (128 dim) for deepSORT tracking. I'm using the framework Detectron2. I saw the following code for features extraction:
image = cv2.imread('my_image.jpg')
height, width = image.shape[:2]
image = torch.as_tensor(image.astype("float32").transpose(2, 0, 1))
inputs = [{"image": image, "height": height, "width": width}]
with torch.no_grad():
images = model.preprocess_image(inputs) # don't forget to preprocess
features = model.backbone(images.tensor) # set of cnn features
proposals, _ = model.proposal_generator(images, features, None) # RPN
features_ = [features[f] for f in model.roi_heads.box_in_features]
box_features = model.roi_heads.box_pooler(features_, [x.proposal_boxes for x in proposals])
box_features = model.roi_heads.box_head(box_features) # features of all 1k candidates
predictions = model.roi_heads.box_predictor(box_features)
pred_instances, pred_inds = model.roi_heads.box_predictor.inference(predictions, proposals)
pred_instances = model.roi_heads.forward_with_given_boxes(features, pred_instances)
# output boxes, masks, scores, etc
pred_instances = model._postprocess(pred_instances, inputs, images.image_sizes) # scale box to orig size
# features of the proposed boxes
feats = box_features[pred_inds]
but i don't understand how to extract the 128 dimensional feature vector, from this piece of code. I would be happy for a little help here. thanks in advance.
