def run_on_image(self, image):
"""
Args:
image (np.ndarray): an image of shape (H, W, C) (in BGR order).
This is the format used by OpenCV.
Returns:
predictions (dict): the output of the model.
vis_output (VisImage): the visualized image output.
"""
vis_output = None
predictions = self.predictor(image)
# Convert image from OpenCV BGR format to Matplotlib RGB format.
image = image[:, :, ::-1]
visualizer = Visualizer(image,
self.metadata,
instance_mode=self.instance_mode)
if "panoptic_seg" in predictions:
panoptic_seg, segments_info = predictions["panoptic_seg"]
vis_output = visualizer.draw_panoptic_seg_predictions(
panoptic_seg.to(self.cpu_device), segments_info)
else:
if "sem_seg" in predictions:
vis_output = visualizer.draw_sem_seg(
predictions["sem_seg"].argmax(dim=0).to(self.cpu_device))
if "instances" in predictions:
instances = predictions["instances"].to(self.cpu_device)
vis_output = visualizer.draw_instance_predictions(
predictions=instances)
return predictions, vis_output
def visualize_predict_data(self,
per_image,
per_instalce,
save_to_file=False):
metadata = self.data_meta
def output(vis, fname):
if not save_to_file:
print(fname)
cv2.imshow("window", vis.get_image()[:, :, ::-1])
cv2.waitKey()
else:
filepath = os.path.join("./", fname)
print("Saving to {} ...".format(filepath))
vis.save(filepath)
scale = 1.0
# Pytorch tensor is in (C, H, W) format
img = per_image["image"].permute(1, 2, 0)
if cfg.INPUT.FORMAT == "BGR":
img = img[:, :, [2, 1, 0]]
else:
img = np.asarray(
Image.fromarray(img, mode=cfg.INPUT.FORMAT).convert("RGB"))
visualizer = Visualizer(img, metadata=metadata, scale=scale)
vis = visualizer.draw_instance_predictions(per_instalce)
output(vis, str(per_image["image_id"]) + ".jpg")
def visualize_training(self, batched_inputs, proposals):
"""
A function used to visualize images and proposals. It shows ground truth
bounding boxes on the original image and up to 20 predicted object
proposals on the original image. Users can implement different
visualization functions for different models.
Args:
batched_inputs (list): a list that contains input to the model.
proposals (list): a list that contains predicted proposals. Both
batched_inputs and proposals should have the same length.
"""
from cvpods.utils import Visualizer
storage = get_event_storage()
max_vis_prop = 20
for input, prop in zip(batched_inputs, proposals):
img = input["image"].cpu().numpy()
assert img.shape[0] == 3, "Images should have 3 channels."
if self.input_format == "BGR":
img = img[::-1, :, :]
img = img.transpose(1, 2, 0)
v_gt = Visualizer(img, None)
v_gt = v_gt.overlay_instances(boxes=input["instances"].gt_boxes)
anno_img = v_gt.get_image()
box_size = min(len(prop.proposal_boxes), max_vis_prop)
v_pred = Visualizer(img, None)
v_pred = v_pred.overlay_instances(
boxes=prop.proposal_boxes[0:box_size].tensor.cpu().numpy()
)
prop_img = v_pred.get_image()
vis_img = np.concatenate((anno_img, prop_img), axis=1)
vis_img = vis_img.transpose(2, 0, 1)
vis_name = " 1. GT bounding boxes 2. Predicted proposals"
storage.put_image(vis_name, vis_img)
def visualize_data(self, per_image, save_to_file=False):
"""
Visualize data from batch_inputs of dataloader.
Args:
per_image (dict): a dict that contains:
* image: Tensor, image in (C, H, W) format.
* instances: Instances
Other information that's included in the original dicts, such as:
* "height", "width" (int): the output resolution of the model, used in inference.
See :meth:`postprocess` for details.
save_to_file: whether save img to disk.
Example:
>>> self.visualize_data(batch_inputs[0])
"""
metadata = self.data_meta
def output(vis, fname):
if not save_to_file:
print(fname)
cv2.imshow("window", vis.get_image()[:, :, ::-1])
cv2.waitKey()
else:
filepath = os.path.join("./", fname)
print("Saving to {} ...".format(filepath))
vis.save(filepath)
scale = 1.0
# Pytorch tensor is in (C, H, W) format
img = per_image["image"].permute(1, 2, 0)
if cfg.INPUT.FORMAT == "BGR":
img = img[:, :, [2, 1, 0]]
else:
img = np.asarray(
Image.fromarray(img, mode=cfg.INPUT.FORMAT).convert("RGB"))
visualizer = Visualizer(img, metadata=metadata, scale=scale)
target_fields = per_image["instances"].get_fields()
labels = [
metadata.thing_classes[i] for i in target_fields["gt_classes"]
]
vis = visualizer.overlay_instances(
labels=labels,
boxes=target_fields.get("gt_boxes", None),
masks=target_fields.get("gt_masks", None),
keypoints=target_fields.get("gt_keypoints", None),
)
output(vis, str(per_image["image_id"]) + ".jpg")
scale = 2.0 if args.show else 1.0
if args.source == "dataloader":
train_data_loader = build_train_loader(cfg)
for batch in train_data_loader:
for per_image in batch:
# Pytorch tensor is in (C, H, W) format
img = per_image["image"].permute(1, 2, 0)
if cfg.INPUT.FORMAT == "BGR":
img = img[:, :, [2, 1, 0]]
else:
img = np.asarray(
Image.fromarray(img,
mode=cfg.INPUT.FORMAT).convert("RGB"))
visualizer = Visualizer(img, metadata=metadata, scale=scale)
target_fields = per_image["instances"].get_fields()
labels = [
metadata.thing_classes[i]
for i in target_fields["gt_classes"]
]
vis = visualizer.overlay_instances(
labels=labels,
boxes=target_fields.get("gt_boxes", None),
masks=target_fields.get("gt_masks", None),
keypoints=target_fields.get("gt_keypoints", None),
)
output(vis, str(per_image["image_id"]) + ".jpg")
else:
dicts = list(
chain.from_iterable(
metadata = dataset.meta
if hasattr(metadata, "thing_dataset_id_to_contiguous_id"):
def dataset_id_map(ds_id):
return metadata.thing_dataset_id_to_contiguous_id[ds_id]
elif "lvis" in args.dataset:
# LVIS results are in the same format as COCO results, but have a different
# mapping from dataset category id to contiguous category id in [0, #categories - 1]
def dataset_id_map(ds_id):
return ds_id - 1
else:
raise ValueError("Unsupported dataset: {}".format(args.dataset))
os.makedirs(args.output, exist_ok=True)
for dic in tqdm.tqdm(dicts):
img = cv2.imread(dic["file_name"], cv2.IMREAD_COLOR)[:, :, ::-1]
basename = os.path.basename(dic["file_name"])
predictions = create_instances(pred_by_image[dic["image_id"]], img.shape[:2])
vis = Visualizer(img, metadata)
vis_pred = vis.draw_instance_predictions(predictions).get_image()
vis = Visualizer(img, metadata)
vis_gt = vis.draw_dataset_dict(dic).get_image()
concat = np.concatenate((vis_pred, vis_gt), axis=1)
cv2.imwrite(os.path.join(args.output, basename), concat[:, :, ::-1])