def fast_rcnn_inference_single_image(boxes, scores, image_shape, score_thresh,
nms_thresh, topk_per_image):
scores = scores[:, :-1]
num_bbox_reg_classes = boxes.shape[1] // 4
# Convert to Boxes to use the `clip` function ...
boxes = Boxes(boxes.reshape(-1, 4))
boxes.clip(image_shape)
boxes = boxes.tensor.view(-1, num_bbox_reg_classes, 4) # R x C x 4
# Select max scores
max_scores, max_classes = scores.max(1) # R x C --> R
num_objs = boxes.size(0)
boxes = boxes.view(-1, 4)
idxs = torch.arange(num_objs).cuda() * num_bbox_reg_classes + max_classes
max_boxes = boxes[idxs] # Select max boxes according to the max scores.
# Apply NMS
keep = nms(max_boxes, max_scores, nms_thresh)
if topk_per_image >= 0:
keep = keep[:topk_per_image]
boxes, scores = max_boxes[keep], max_scores[keep]
result = Instances(image_shape)
result.pred_boxes = Boxes(boxes)
result.scores = scores
result.pred_classes = max_classes[keep]
return result, keep
def fast_rcnn_inference_single_image(
boxes, scores, image_shape, nms_thresh, topk_per_image
):
"""
Single-image inference. Return bounding-box detection results by thresholding
on scores and applying non-maximum suppression (NMS).
Args:
Same as `fast_rcnn_inference`, but with boxes, scores, and image shapes
per image.
Returns:
Same as `fast_rcnn_inference`, but for only one image.
"""
class_distr_scores = scores.clone()
scores = scores[:, :-1]
num_bbox_reg_classes = boxes.shape[1] // 4
# Convert to Boxes to use the `clip` function ...
boxes = Boxes(boxes.reshape(-1, 4))
boxes.clip(image_shape)
boxes = boxes.tensor.view(-1, num_bbox_reg_classes, 4) # R x C x 4
# Select max scores
max_scores, max_classes = scores.max(1) # R x C --> R
num_objs = boxes.size(0)
boxes = boxes.view(-1, 4)
num_objs = torch.arange(num_objs)
if torch.cuda.is_available():
num_objs = num_objs.cuda()
idxs = num_objs * num_bbox_reg_classes + max_classes
max_boxes = boxes[idxs] # Select max boxes according to the max scores.
# Apply NMS
keep = nms(max_boxes, max_scores, nms_thresh)
if topk_per_image >= 0:
keep = keep[:topk_per_image]
boxes, scores = max_boxes[keep], max_scores[keep]
result = Instances(image_shape)
result.pred_boxes = Boxes(boxes)
class_distr_scores = class_distr_scores[keep]
# we set the background probability to 0
class_distr_scores[:, -1] = 0.0
result.scores = class_distr_scores
return result, keep
def fast_rcnn_inference_single_image(boxes,
scores,
image_shape,
score_thresh,
nms_thresh,
topk_per_image,
device,
preferred_labels=[],
tokens=[],
tokenizer=None):
scores = scores[:, :-1]
num_bbox_reg_classes = boxes.shape[1] // 4
# Convert to Boxes to use the `clip` function ...
boxes = Boxes(boxes.reshape(-1, 4))
boxes.clip(image_shape)
boxes = boxes.tensor.view(-1, num_bbox_reg_classes, 4) # R x C x 4
# Select max scores
max_scores, max_classes = scores.max(1) # R x C --> R
num_objs = boxes.size(0)
boxes = boxes.view(-1, 4)
idxs = torch.arange(num_objs).cuda(
device) * num_bbox_reg_classes + max_classes
max_boxes = boxes[idxs] # Select max boxes according to the max scores.
# Apply NMS
keep = nms(max_boxes, max_scores, nms_thresh)
# calculate the closes tokens
words = get_image_labels2(preferred_labels, max_classes[keep].tolist(),
keep.tolist())
relevant = []
others = []
class_list = []
for word, c, i in words:
tok = tokenizer.vocab.get(word, tokenizer.vocab["[UNK]"])
## inserting the relevant first
if tok in tokens:
relevant.append(i)
## repeated predictions go last.
elif c in class_list:
class_list.append(c)
others.append(i)
## Inserting varied predictions first
else:
class_list.append(c)
others.insert(i, 0)
keep = torch.tensor(relevant + others, device=device)
#remove duplicate classes......
if topk_per_image >= 0:
keep = keep[:topk_per_image]
keep = keep[torch.randperm(keep.size()[0])]
boxes, scores = max_boxes[keep], max_scores[keep]
result = Instances(image_shape)
result.pred_boxes = Boxes(boxes)
result.scores = scores
result.pred_classes = max_classes[keep]
return result, keep
