def forward_test(self, images):
images = to_image_list(images).to(self.device)
features = self.backbone(images.tensors)
results = self.rpn(images, features)
if hasattr(self, "roi_heads"):
results = self.roi_heads(features, results)
return results
def forward_train(self, images, targets):
images = to_image_list(images).to(self.device)
targets = [target.to(self.device) for target in targets]
features = self.backbone(images.tensors)
proposals, losses = self.rpn(images, features, targets)
if hasattr(self, "roi_heads"):
losses.update(self.roi_heads(features, proposals, targets))
return losses
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