def render_frame(prms):
frame_id, frame_path, tubelets, rendered_frames_dir, cfg = prms
rendered_frame_path = rendered_frames_dir / frame_path.name
if rendered_frame_path.exists():
return
tubelet_ids = []
tubelet_instances = []
tubelet_instance_projections = []
for tubelet_id, tubelet in enumerate(tubelets):
tubelet_ids.append(tubelet_id)
tubelet_instances.append(tubelet.get_instance(frame_id))
tubelet_instance_projections.append(
tubelet.get_projected_instance(frame_id))
frame = cv2.imread(str(frame_path))
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
frame = cv2.merge([frame, frame, frame])
visualizer._SMALL_OBJECT_AREA_THRESH = 1
v = visualizer.Visualizer(frame[:, :, ::-1],
MetadataCatalog.get(cfg.DATASETS.TRAIN[0]),
scale=1.2)
v = draw_instance_predictions(v, tubelet_ids, tubelet_instances,
tubelet_instance_projections)
cv2.imwrite(str(rendered_frame_path), v.get_image()[:, :, ::-1])
def pred_viz(im, outputs, metadata, output_path):
v = visualizer.Visualizer(im[:, :, ::-1],
metadata=metadata,
instance_mode=ColorMode.SEGMENTATION)
v = v.draw_instance_predictions(outputs["instances"].to("cpu"))
if args.save_viz:
cv2.imwrite(output_path, v.get_image()[:, :, ::-1])
cv2.imshow('', v.get_image()[:, :, ::-1])
cv2.waitKey(0)
def visualize(args, mode, _appcfg):
name = "hmd"
subset = "train"
dataset_name = get_dataset_name(name, subset)
metadata = load_and_register_dataset(name, subset, _appcfg)
dataset_dicts = DatasetCatalog.get(dataset_name)
N = 30
for d in random.sample(dataset_dicts, N):
# print("d: {}".format(d))
# print("annos: {}".format(d.get("annotations", None)))
# print("annos: {}".format(d.get("annotations", None)[0]))
image_filepath = d["file_name"]
# image_filepath = "/aimldl-dat/data-gaze/AIML_Annotation/ods_job_230119/images/images-p2-050219_AT2/291018_114342_16718_zed_l_057.jpg"
# image_filepath = "/aimldl-dat/data-gaze/AIML_Annotation/ods_job_230119/images/images-p2-050219_AT2/291018_114252_16716_zed_l_099.jpg"
im = cv2.imread(image_filepath)
# visualize_predictions(im, outputs, metadata)
v = visualizer.Visualizer(im[:, :, ::-1], metadata=metadata)
v = v.draw_dataset_dict(d)
cv2.imshow('', v.get_image()[:, :, ::-1])
cv2.waitKey(0)
def draw_vis(
input: Dict[str, Any],
metadata: Optional[Metadata],
scale: float = 1.0,
draw_instances: bool = True,
) -> np.ndarray:
"""
input (Dict[str, Any]): a dict containing an "image" key (format
provided by "image_format" key if not RGB) and an optional
"instances" key to draw instances.
note: the "instances" should be on cpu.
"""
img = input["image"]
if input.get("image_format", "RGB") != "RGB":
img = convert_image_to_rgb(img, input["image_format"])
if torch.is_tensor(img):
img = img.numpy().astype("uint8")
if draw_instances and "instances" in input:
vis = visualizer.Visualizer(img, metadata, scale=scale)
visimg = vis.draw_instance_predictions(input["instances"])
img = visimg.get_image()
return img
def visualize(args, mode, _appcfg):
name = "hmd"
subset = "train"
if args.subset:
subset = args.subset
dataset_name = get_dataset_name(name, subset)
metadata = load_and_register_dataset(name, subset, _appcfg)
dataset_dicts = DatasetCatalog.get(dataset_name)
N = 20
for d in random.sample(dataset_dicts, N):
# log.debug("d: {}".format(d))
# log.debug("annos: {}".format(d.get("annotations", None)))
# log.debug("annos: {}".format(d.get("annotations", None)[0]))
image_filepath = d["file_name"]
im = cv2.imread(image_filepath)
v = visualizer.Visualizer(im[:, :, ::-1], metadata=metadata)
v = v.draw_dataset_dict(d)
cv2.imshow('', v.get_image()[:, :, ::-1])
cv2.waitKey(0)
def predict(args, mode, _appcfg):
name = "hmd"
subset = "val"
BASE_IMAGE_PATH = "/aimldl-dat/samples/Trafic_Signs"
if args.path:
BASE_IMAGE_PATH = args.path
PREDICTION_OUTPUT_PATH = "/aimldl-dat/samples/Predictions"
print("BASE_IMAGE_PATH: {}".format(BASE_IMAGE_PATH))
dataset_name = get_dataset_name(name, subset)
cfg = config.get_cfg()
# cfg.merge_from_file("/aimldl-cod/external/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
cfg.merge_from_file(
model_zoo.get_config_file(
"COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.DATALOADER.NUM_WORKERS = 2
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.00025
# cfg.SOLVER.MAX_ITER = 300 # 300 iterations seems good enough, but you can certainly train longer
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128 # faster, and good enough for this toy dataset
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 3
cfg.OUTPUT_DIR = "/codehub/apps/detectron2/release"
cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7 # set the testing threshold for this model
cfg.DATASETS.TEST = (dataset_name)
# print("cfg: {}".format(cfg.dump()))
#Predict from a directory
metadata = MetadataCatalog.get(dataset_name).set(
thing_classes=['signage', 'traffic_light', 'traffic_sign'])
# print("Metadata: {}".format(metadata))
predictor = DefaultPredictor(cfg)
for image in os.listdir(BASE_IMAGE_PATH):
image_filepath = os.path.join(BASE_IMAGE_PATH, image)
output_path = PREDICTION_OUTPUT_PATH + "/" + image
# image_filepath = "/aimldl-dat/data-gaze/AIML_Annotation/ods_job_230119/images/images-p2-050219_AT2/291018_114342_16718_zed_l_057.jpg"
# image_filepath = "/aimldl-dat/data-gaze/AIML_Annotation/ods_job_230119/images/images-p2-050219_AT2/291018_114252_16716_zed_l_099.jpg"
# print("image_filepath: {}".format(image_filepath))
im = cv2.imread(image_filepath)
outputs = predictor(im)
# visualize_predictions(im, outputs, metadata)
v = visualizer.Visualizer(im[:, :, ::-1],
metadata=metadata,
instance_mode=ColorMode.SEGMENTATION)
v = v.draw_instance_predictions(outputs["instances"].to("cpu"))
# cv2.imwrite(output_path, v.get_image()[:, :, ::-1])
cv2.imshow('', v.get_image()[:, :, ::-1])
cv2.waitKey(0)
"category_id": 0,
"iscrowd": 0
}
objs.append(obj)
record["annotations"] = objs
dataset_dicts.append(record)
return dataset_dicts
for d in ["train", "val"]:
DatasetCatalog.register(
"balloon_" + d,
lambda d=d: get_balloon_dicts(
"/aimldl-dat/data-public/balloon_dataset/balloon/" + d))
MetadataCatalog.get("balloon_" + d).set(thing_classes=["balloon"])
balloon_metadata = MetadataCatalog.get("balloon_train")
dataset_dicts = get_balloon_dicts(
"/aimldl-dat/data-public/balloon_dataset/balloon/train")
for d in random.sample(dataset_dicts, 3):
img = cv2.imread(d["file_name"])
viz = visualizer.Visualizer(img[:, :, ::-1],
metadata=balloon_metadata,
scale=0.5)
vis = viz.draw_dataset_dict(d)
# vis.save("/aimldl-dat/temp/det02.jpg")
# cv2.imwrite("/aimldl-dat/temp/det01.jpg", vis.get_image()[:, :, ::-1])
cv2.imshow('', vis.get_image()[:, :, ::-1])
# cv2.imshow('', img)
cv2.waitKey(0)
# "surfboard", "tennis racket", "bottle", "wine glass", "cup",
# "fork", "knife", "spoon", "bowl", "banana", "apple",
# "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza",
# "donut", "cake", "chair", "couch", "potted plant", "bed",
# "dining table", "toilet", "tv", "laptop", "mouse", "remote",
# "keyboard", "cell phone", "microwave", "oven", "toaster",
# "sink", "refrigerator", "book", "clock", "vase", "scissors",
# "teddy bear", "hair drier", "toothbrush"])
metadata = MetadataCatalog.get(dataset_name)
print("metadata: {}".format(metadata))
# MetadataCatalog.get(dataset_name).set(json_file=json_file, image_root=image_root, evaluator_type=dataset_name, **metadata)
metadata.thing_classes = ['person', 'bicycle', 'car', 'motorcycle', 'airplane']
metadata.thing_dataset_id_to_contiguous_id = {1: 0, 2: 1, 3: 2, 4: 3, 5: 4}
# MetadataCatalog.get(dataset_name).set(thing_classes=thing_classes, metadata=thing_dataset_id_to_contiguous_id)
# MetadataCatalog.get(dataset_name).set(json_file=json_file, image_root=image_root, evaluator_type=dataset_name, metadata={})
N = 2
for d in random.sample(dataset_dicts_train, N):
img = cv2.imread(d["file_name"])
viz = visualizer.Visualizer(img[:, :, ::-1], metadata=metadata, scale=1)
vis = viz.draw_dataset_dict(d)
# vis.save("/aimldl-dat/temp/det02.jpg")
# cv2.imwrite("/aimldl-dat/temp/det01.jpg", vis.get_image()[:, :, ::-1])
cv2.imshow('', vis.get_image()[:, :, ::-1])
# cv2.imshow('', img)
cv2.waitKey(0)