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 top-scoring 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.
"""
storage = get_event_storage()
max_vis_prop = 20
for input, prop in zip(batched_inputs, proposals):
img = input["image"]
img = convert_image_to_rgb(img.permute(1, 2, 0), self.input_format)
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 = "Left: GT bounding boxes; Right: Predicted proposals"
storage.put_image(vis_name, vis_img)
break # only visualize one image in a batch
def draw_instance_predictions(self, frame, predictions):
"""
Draw instance-level prediction results on an image.
Args:
frame (ndarray): an RGB image of shape (H, W, C), in the range [0, 255].
predictions (Instances): the output of an instance detection
model. Following fields will be used to draw:
"pred_boxes", "pred_classes", "scores".
Returns:
output (VisImage): image object with visualizations.
"""
frame_visualizer = Visualizer(frame, self.metadata)
num_instances = len(predictions)
if num_instances == 0:
return frame_visualizer.output
boxes = predictions.pred_boxes.tensor.numpy() if predictions.has(
"pred_boxes") else None
scores = predictions.scores if predictions.has("scores") else None
classes = predictions.pred_classes.numpy() if predictions.has(
"pred_classes") else None
detected = [
_DetectedInstance(classes[i], boxes[i], color=None, ttl=8)
for i in range(num_instances)
]
colors = self._assign_colors(detected)
labels = _create_text_labels(classes, scores,
self.metadata.get("thing_classes", None))
if self._instance_mode == ColorMode.IMAGE_BW:
# any() returns uint8 tensor
frame_visualizer.output.img = frame_visualizer._create_grayscale_image(
)
alpha = 0.3
else:
alpha = 0.5
frame_visualizer.overlay_instances(
boxes=boxes, # boxes are a bit distracting
labels=labels,
assigned_colors=colors,
alpha=alpha,
)
return frame_visualizer.output
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 "instances" in predictions:
instances = predictions["instances"].to(self.cpu_device)
vis_output = visualizer.draw_instance_predictions(
predictions=instances)
return predictions, vis_output
train_data_loader = build_detection_train_loader(cfg, mapper=mapper)
for batch in train_data_loader:
for per_image in batch:
# type(per_image), per_images.keys()
# <class 'dict'>, dict_keys(['file_name', 'image_id', 'height', 'width', 'image', 'instances'])
# 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.keys() => dict_keys(['gt_boxes', 'gt_classes'])
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),
)
# modified: voc I=1 in any case
num_instances = len(per_image['instances'])
output(
vis, "I{}_".format(num_instances) +
return dataset_dicts
if __name__ == "__main__":
"""
Test the LVIS json dataset loader.
Usage:
python -m fsdet.data.datasets.lvis \
path/to/json path/to/image_root dataset_name vis_limit
"""
import sys
import numpy as np
from fsdet.utils.logger import setup_logger
from PIL import Image
from fsdet.utils.visualizer import Visualizer
logger = setup_logger(name=__name__)
meta = MetadataCatalog.get(sys.argv[3])
dicts = load_lvis_json(sys.argv[1], sys.argv[2], sys.argv[3])
logger.info("Done loading {} samples.".format(len(dicts)))
dirname = "lvis-data-vis"
os.makedirs(dirname, exist_ok=True)
for d in dicts[:int(sys.argv[4])]:
img = np.array(Image.open(d["file_name"]))
visualizer = Visualizer(img, metadata=meta)
vis = visualizer.draw_dataset_dict(d)
fpath = os.path.join(dirname, os.path.basename(d["file_name"]))
vis.save(fpath)
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])