def __getitem__(self, index):
boxes, labels = self.get_annotation(index)
image = self._read_image(index)
if self.transform:
image, boxes, labels = self.transform(image, boxes, labels)
if self.target_transform:
boxes, labels = self.target_transform(boxes, labels)
target = Container(boxes=boxes, labels=labels)
return image, target, index
def __getitem__(self, index):
image = self.images[index]
boxes, labels = self.get_annotation(index)
image = image[:, :, None].repeat(3, -1)
if self.transform:
image, boxes, labels = self.transform(image, boxes, labels)
if self.target_transform:
boxes, labels = self.target_transform(boxes, labels)
target = Container(boxes=boxes, labels=labels)
return image, target, index
def __call__(self, batch):
transposed_batch = list(zip(*batch))
images = default_collate(transposed_batch[0])
img_ids = default_collate(transposed_batch[2])
if self.is_train:
list_targets = transposed_batch[1]
targets = Container(
{key: default_collate([d[key] for d in list_targets]) for key in list_targets[0]}
)
else:
targets = None
return images, targets, img_ids
def __getitem__(self, index):
image_id = self.ids[index]
boxes, labels = self._get_annotation(image_id)
image = self._read_image(image_id)
if self.transform:
image, boxes, labels = self.transform(image, boxes, labels)
if self.target_transform:
boxes, labels = self.target_transform(boxes, labels)
targets = Container(
boxes=boxes,
labels=labels,
)
return image, targets, index
def __call__(self, detections):
"""
Post processor of detections when we are doing inference.
Applies two filter operations to remove all prior boxes that does not include an object:
Confidence thresholding and non-maximum suppression.
"""
batches_scores, batches_boxes = detections
device = batches_scores.device
batch_size = batches_scores.size(0)
results = []
for batch_id in range(batch_size):
scores, boxes = batches_scores[batch_id], batches_boxes[
batch_id] # (N, #CLS) (N, 4)
num_boxes = scores.shape[0]
num_classes = scores.shape[1]
boxes = boxes.view(num_boxes, 1, 4).expand(num_boxes, num_classes,
4)
labels = torch.arange(num_classes, device=device)
labels = labels.view(1, num_classes).expand_as(scores)
# remove predictions with the background label
boxes = boxes[:, 1:]
scores = scores[:, 1:]
labels = labels[:, 1:]
# batch everything, by making every class prediction be a separate instance
boxes = boxes.reshape(-1, 4)
scores = scores.reshape(-1)
labels = labels.reshape(-1)
# remove low scoring boxes
indices = torch.nonzero(
scores > self.cfg.TEST.CONFIDENCE_THRESHOLD).squeeze(1)
boxes, scores, labels = boxes[indices], scores[indices], labels[
indices]
boxes[:, 0::2] *= self.width
boxes[:, 1::2] *= self.height
keep = batched_nms(boxes, scores, labels,
self.cfg.TEST.NMS_THRESHOLD)
# keep only topk scoring predictions
keep = keep[:self.cfg.TEST.MAX_PER_IMAGE]
boxes, scores, labels = boxes[keep], scores[keep], labels[keep]
container = Container(boxes=boxes, labels=labels, scores=scores)
container.img_width = self.width
container.img_height = self.height
results.append(container)
return results
def __getitem__(self, index):
image_id = self.image_ids[index]
boxes, labels, is_difficult = self._get_annotation(image_id)
if not self.keep_difficult:
boxes = boxes[is_difficult == 0]
labels = labels[is_difficult == 0]
image = self._read_image(image_id)
if self.transform:
image, boxes, labels = self.transform(image, boxes, labels)
if self.target_transform:
boxes, labels = self.target_transform(boxes, labels)
targets = Container(
boxes=boxes,
labels=labels,
)
return image, targets, index
def __call__(self, detections):
batches_scores, batches_boxes = detections
device = batches_scores.device
batch_size = batches_scores.size(0)
results = []
for batch_id in range(batch_size):
scores, boxes = batches_scores[batch_id], batches_boxes[
batch_id] # (N, #CLS) (N, 4)
num_boxes = scores.shape[0]
num_classes = scores.shape[1]
boxes = boxes.view(num_boxes, 1, 4).expand(num_boxes, num_classes,
4)
labels = torch.arange(num_classes, device=device)
labels = labels.view(1, num_classes).expand_as(scores)
# remove predictions with the background label
boxes = boxes[:, 1:]
scores = scores[:, 1:]
labels = labels[:, 1:]
# batch everything, by making every class prediction be a separate instance
boxes = boxes.reshape(-1, 4)
scores = scores.reshape(-1)
labels = labels.reshape(-1)
# remove low scoring boxes
indices = torch.nonzero(
scores > self.cfg.TEST.CONFIDENCE_THRESHOLD).squeeze(1)
boxes, scores, labels = boxes[indices], scores[indices], labels[
indices]
boxes[:, 0::2] *= self.width
boxes[:, 1::2] *= self.height
keep = batched_nms(boxes, scores, labels,
self.cfg.TEST.NMS_THRESHOLD)
# keep only topk scoring predictions
keep = keep[:self.cfg.TEST.MAX_PER_IMAGE]
boxes, scores, labels = boxes[keep], scores[keep], labels[keep]
container = Container(boxes=boxes, labels=labels, scores=scores)
container.img_width = self.width
container.img_height = self.height
results.append(container)
return results