def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Webcam Demo")
parser.add_argument(
"--config-file",
default="configs/caffe2/e2e_mask_rcnn_X_101_32x8d_FPN_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument(
"--confidence-threshold",
type=float,
default=0.6,
help="Minimum score for the prediction to be shown",
)
parser.add_argument(
"--min-image-size",
type=int,
default=256,
help="Smallest size of the image to feed to the model. "
"Model was trained with 800, which gives best results",
)
parser.add_argument(
"--show-mask-heatmaps",
dest="show_mask_heatmaps",
help="Show a heatmap probability for the top masks-per-dim masks",
action="store_true",
)
parser.add_argument(
"--masks-per-dim",
type=int,
default=2,
help="Number of heatmaps per dimension to show",
)
parser.add_argument(
"opts",
help="Modify model config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
parser.add_argument("--svo-filename",
help="Optional SVO input filepath",
default=None)
args = parser.parse_args()
# load config from file and command-line arguments
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
# prepare object that handles inference plus adds predictions on top of image
coco_demo = COCODemo(
cfg,
confidence_threshold=args.confidence_threshold,
show_mask_heatmaps=args.show_mask_heatmaps,
masks_per_dim=args.masks_per_dim,
min_image_size=args.min_image_size,
)
init_cap_params = sl.InitParameters()
if args.svo_filename:
print("Loading SVO file " + args.svo_filename)
init_cap_params.set_from_svo_file(args.svo_filename)
init_cap_params.svo_real_time_mode = True
init_cap_params.camera_resolution = sl.RESOLUTION.HD720
init_cap_params.depth_mode = sl.DEPTH_MODE.ULTRA
init_cap_params.coordinate_units = sl.UNIT.METER
init_cap_params.depth_stabilization = True
init_cap_params.camera_image_flip = sl.FLIP_MODE.AUTO
init_cap_params.coordinate_system = sl.COORDINATE_SYSTEM.RIGHT_HANDED_Y_UP
cap = sl.Camera()
if not cap.is_opened():
print("Opening ZED Camera...")
status = cap.open(init_cap_params)
if status != sl.ERROR_CODE.SUCCESS:
print(repr(status))
exit()
display = True
runtime = sl.RuntimeParameters()
left = sl.Mat()
ptcloud = sl.Mat()
depth_img = sl.Mat()
depth = sl.Mat()
res = sl.Resolution(1280, 720)
py_transform = sl.Transform(
) # First create a Transform object for TrackingParameters object
tracking_parameters = sl.PositionalTrackingParameters(
init_pos=py_transform)
tracking_parameters.set_as_static = True
err = cap.enable_positional_tracking(tracking_parameters)
if err != sl.ERROR_CODE.SUCCESS:
exit(1)
running = True
keep_people_only = True
if coco_demo.cfg.MODEL.MASK_ON:
print("Mask enabled!")
if coco_demo.cfg.MODEL.KEYPOINT_ON:
print("Keypoints enabled!")
while running:
start_time = time.time()
err_code = cap.grab(runtime)
if err_code != sl.ERROR_CODE.SUCCESS:
break
cap.retrieve_image(left, sl.VIEW.LEFT, resolution=res)
cap.retrieve_image(depth_img, sl.VIEW.DEPTH, resolution=res)
cap.retrieve_measure(depth, sl.MEASURE.DEPTH, resolution=res)
cap.retrieve_measure(ptcloud, sl.MEASURE.XYZ, resolution=res)
ptcloud_np = np.array(ptcloud.get_data())
img = cv2.cvtColor(left.get_data(), cv2.COLOR_RGBA2RGB)
prediction = coco_demo.select_top_predictions(
coco_demo.compute_prediction(img))
# Keep people only
if keep_people_only:
labels_tmp = prediction.get_field("labels")
people_coco_label = 1
keep = torch.nonzero(labels_tmp == people_coco_label).squeeze(1)
prediction = prediction[keep]
composite = img.copy()
humans_3d = None
masks_3d = None
if coco_demo.show_mask_heatmaps:
composite = coco_demo.create_mask_montage(composite, prediction)
composite = coco_demo.overlay_boxes(composite, prediction)
if coco_demo.cfg.MODEL.MASK_ON:
masks_3d = get_masks3d(prediction, depth)
composite = coco_demo.overlay_mask(composite, prediction)
if coco_demo.cfg.MODEL.KEYPOINT_ON:
# Extract 3D skeleton from the ZED depth
humans_3d = get_humans3d(prediction, ptcloud_np)
composite = coco_demo.overlay_keypoints(composite, prediction)
if True:
overlay_distances(prediction, get_boxes3d(prediction, ptcloud_np),
composite, humans_3d, masks_3d)
composite = coco_demo.overlay_class_names(composite, prediction)
print(" Time: {:.2f} s".format(time.time() - start_time))
if display:
cv2.imshow("COCO detections", composite)
cv2.imshow("ZED Depth", depth_img.get_data())
key = cv2.waitKey(10)
if key == 27:
break # esc to quit
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--ckpt",
help=
"The path to the checkpoint for test, default is the latest checkpoint.",
default=None,
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
config_file = args.config_file #"../configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml"
# update the config options with the config file
cfg.merge_from_file(config_file)
# manual override some options
cfg.merge_from_list(["MODEL.DEVICE", "cpu"])
cfg.merge_from_list(args.opts)
cfg.freeze()
for conf_thresh in [0.1, 0.3, 0.5, 0.7, 0.9]:
coco_demo = COCODemo(
cfg,
min_image_size=800,
confidence_threshold=conf_thresh,
)
paths_catalog = import_file("maskrcnn_benchmark.config.paths_catalog",
cfg.PATHS_CATALOG, True)
DatasetCatalog = paths_catalog.DatasetCatalog
for dataset_name in cfg.DATASETS.TEST:
print(dataset_name)
dataset = DatasetCatalog.get(dataset_name)
# print(dataset)
# print(len(dataset))
print(dataset)
dataset = FolderDataset(dataset['args']['data_dir'],
dataset['args']['split'])
COCODemo.CATEGORIES = dataset.CLASSES
for image, target, index in tqdm(dataset):
image_name = dataset.img_files[index].split("/")[-1]
image = np.array(image)
all_labels = [
coco_demo.CATEGORIES[i]
for i in target.get_field("labels").tolist()
]
if len(all_labels) > 1:
print(all_labels)
### GROND TRUTH
result = image.copy()
if coco_demo.show_mask_heatmaps:
return coco_demo.create_mask_montage(result, target)
result = coco_demo.overlay_boxes(result, target)
# result = coco_demo.overlay_boxes(result, target)
if coco_demo.cfg.MODEL.MASK_ON:
result = coco_demo.overlay_mask(result, target)
if coco_demo.cfg.MODEL.KEYPOINT_ON:
result = coco_demo.overlay_keypoints(result, target)
# result = coco_demo.overlay_class_names(result, top_predictions)
labels = [
coco_demo.CATEGORIES[i]
for i in target.get_field("labels").tolist()
]
boxes = target.bbox
for box, label in zip(boxes, labels):
x, y = box[:2]
cv2.putText(result, label, (x, y),
cv2.FONT_HERSHEY_SIMPLEX, 5, (255, 255, 255),
1)
result = Image.fromarray(result)
for label_GT in all_labels:
if ".tif" in image_name:
out = os.path.join(
cfg.OUTPUT_DIR, f"inference_{conf_thresh}",
dataset_name, label_GT,
image_name.replace(".tif", "_GT.tif"))
if ".jpg" in image_name:
out = os.path.join(
cfg.OUTPUT_DIR, f"inference_{conf_thresh}",
dataset_name, label_GT,
image_name.replace(".jpg", "_GT.jpg"))
if ".JPG" in image_name:
out = os.path.join(
cfg.OUTPUT_DIR, f"inference_{conf_thresh}",
dataset_name, label_GT,
image_name.replace(".JPG", "_GT.JPG"))
os.makedirs(os.path.dirname(out), exist_ok=True)
# result.save(out)
if not os.path.exists(out):
result.save(out)
### PREDICTION
predictions = coco_demo.compute_prediction(image)
top_predictions = coco_demo.select_top_predictions(predictions)
# print(top_predictions)
result = image.copy()
if coco_demo.show_mask_heatmaps:
return coco_demo.create_mask_montage(
result, top_predictions)
result = coco_demo.overlay_boxes(result, top_predictions)
# result = coco_demo.overlay_boxes(result, target)
if coco_demo.cfg.MODEL.MASK_ON:
result = coco_demo.overlay_mask(result, top_predictions)
if coco_demo.cfg.MODEL.KEYPOINT_ON:
result = coco_demo.overlay_keypoints(
result, top_predictions)
result = coco_demo.overlay_class_names(result, top_predictions)
result = Image.fromarray(result)
for label_GT in all_labels:
out = os.path.join(cfg.OUTPUT_DIR,
f"inference_{conf_thresh}",
dataset_name, label_GT, image_name)
os.makedirs(os.path.dirname(out), exist_ok=True)
if not os.path.exists(out):
result.save(out)
### PREDICTION BEST only
# predictions = coco_demo.compute_prediction(image)
top_predictions = coco_demo.select_top_predictions(
predictions, best_only=True)
# print(top_predictions)
result = image.copy()
if coco_demo.show_mask_heatmaps:
return coco_demo.create_mask_montage(
result, top_predictions)
result = coco_demo.overlay_boxes(result, top_predictions)
# result = coco_demo.overlay_boxes(result, target)
if coco_demo.cfg.MODEL.MASK_ON:
result = coco_demo.overlay_mask(result, top_predictions)
if coco_demo.cfg.MODEL.KEYPOINT_ON:
result = coco_demo.overlay_keypoints(
result, top_predictions)
result = coco_demo.overlay_class_names(result, top_predictions)
result = Image.fromarray(result)
for label_GT in all_labels:
if ".tif" in image_name:
out = os.path.join(
cfg.OUTPUT_DIR, f"inference_{conf_thresh}",
dataset_name, label_GT,
image_name.replace(".tif", "_best.tif"))
if ".jpg" in image_name:
out = os.path.join(
cfg.OUTPUT_DIR, f"inference_{conf_thresh}",
dataset_name, label_GT,
image_name.replace(".jpg", "_best.jpg"))
if ".JPG" in image_name:
out = os.path.join(
cfg.OUTPUT_DIR, f"inference_{conf_thresh}",
dataset_name, label_GT,
image_name.replace(".JPG", "_best.JPG"))
os.makedirs(os.path.dirname(out), exist_ok=True)
if not os.path.exists(out):
result.save(out)
min_image_size=800,
confidence_threshold=0.6)
fourcc = cv2.VideoWriter_fourcc(*'XVID')
cap = cv2.VideoCapture('tmp/S2_Cars_day_cut.mp4')
out = cv2.VideoWriter('tmp/test_S2_Cars_day.avi', fourcc, 20.0, size)
index = 0
while (cap.isOpened()):
ret, frame_bgr = cap.read()
frame_bgr = cv2.resize(frame_bgr, size)
index += 1
if not ret:
break
with log.Tick():
predictions = coco_demo.compute_prediction(frame_bgr)
top_predictions = coco_demo.select_top_predictions(predictions)
result = frame_bgr.copy()
result = coco_demo.overlay_mask(result, top_predictions)
result = coco_demo.overlay_boxes(result, top_predictions)
result = coco_demo.overlay_class_names(result, top_predictions)
cv2.imshow('result', result)
out.write(result)
if 32 == cv2.waitKey(1):
break
out.release()
