def forward(self, images, targets=None):
"""
Arguments:
images (list[Tensor] or ImageList): images to be processed
targets (list[BoxList]): ground-truth boxes present in the image (optional)
Returns:
result (list[BoxList] or dict[Tensor]): the output from the model.
During training, it returns a dict[Tensor] which contains the losses.
During testing, it returns list[BoxList] contains additional fields
like `scores`, `labels` and `mask` (for Mask R-CNN models).
"""
if self.training and targets is None:
raise ValueError("In training mode, targets should be passed")
images = to_image_list(images)
features = self.backbone(images.tensors)
proposals, proposal_losses = self.rpn(images, features, targets)
if self.roi_heads:
x, result, detector_losses = self.roi_heads(
features, proposals, targets)
else:
# RPN-only models don't have roi_heads
x = features
result = proposals
detector_losses = {}
if self.training:
losses = {}
losses.update(detector_losses)
losses.update(proposal_losses)
return losses
return result
def __call__(self, batch):
transposed_batch = list(zip(*batch))
images = to_image_list(transposed_batch[0], self.size_divisible)
if self.produce:
img_idx = transposed_batch[1]
img_ids = transposed_batch[2]
return images, img_idx, img_ids
else:
targets = transposed_batch[1]
img_ids = transposed_batch[2]
img_name = transposed_batch[3]
return images, targets, img_ids, img_name
def im_detect_bbox(model, images, target_scale, target_max_size, device):
"""
Performs bbox detection on the original image.
"""
transform = TT.Compose([
T.Resize(target_scale, target_max_size),
TT.ToTensor(),
T.Normalize(mean=cfg.INPUT.PIXEL_MEAN,
std=cfg.INPUT.PIXEL_STD,
to_bgr255=cfg.INPUT.TO_BGR255)
])
images = [transform(image) for image in images]
images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
return model(images.to(device))
def im_detect_bbox_hflip(model, images, target_scale, target_max_size, device):
"""
Performs bbox detection on the horizontally flipped image.
Function signature is the same as for im_detect_bbox.
"""
transform = TT.Compose([
T.Resize(target_scale, target_max_size),
TT.RandomHorizontalFlip(1.0),
TT.ToTensor(),
T.Normalize(mean=cfg.INPUT.PIXEL_MEAN,
std=cfg.INPUT.PIXEL_STD,
to_bgr255=cfg.INPUT.TO_BGR255)
])
images = [transform(image) for image in images]
images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
boxlists = model(images.to(device))
# Invert the detections computed on the flipped image
boxlists_inv = [boxlist.transpose(0) for boxlist in boxlists]
return boxlists_inv
def __call__(self, batch):
transposed_batch = list(zip(*batch))
images = to_image_list(transposed_batch[0], self.size_divisible)
targets = transposed_batch[1]
img_ids = transposed_batch[2]
return images, targets, img_ids