def predict(pred_func, input_file):
img = cv2.imread(input_file, cv2.IMREAD_COLOR)
results = detect_one_image(img, pred_func)
final = draw_final_outputs(
img, results) # image contain boxes,labels and scores
viz = np.concatenate((img, final), axis=1)
tpviz.interactive_imshow(viz)
def process_image(detector, img_path):
# Detect faces
image_bgr = cv2.imread(img_path)
face_results = detector.detect(image_bgr, rgb=False)
# Select best face to ignore false positives, such as faces on the clothes
best_faces = pick_best_faces(face_results, args.max_num_faces)
# Visualize detected faces for quick verification
nonlocal n_visualize
if n_visualize > 0:
image_bgr = draw_final_outputs(
image_bgr, best_faces, show_ids=face_detector.get_class_ids())
cv2.imshow('face detection', image_bgr)
cv2.waitKey(0)
n_visualize -= 1
return best_faces
parser.add_argument(
'--config',
default='',
type=str,
help='Configurations of object detection model',
nargs='+'
)
args = parser.parse_args()
if args.config:
cfg.update_args(args.config)
obj_detector = TensorPackDetector('/root/datasets/figmarcnn/checkpoint')
img = cv2.imread('/root/datasets/img-folder/a.png', cv2.IMREAD_COLOR)
results = obj_detector.detect(img, rgb=False)
final = draw_final_outputs(img, results) # image contain boxes,labels and scores
viz = np.concatenate((img, final), axis=1)
tpviz.interactive_imshow(viz)
'''
--image
/root/datasets/myimage/8.jpeg
--cam
0
--obj_model
two-stage
--obj_ckpt
/root/datasets/figmarcnn/checkpoint
--obj_config
def visualize(model, model_path, nr_visualize=100, output_dir='output'):
"""
Visualize some intermediate results (proposals, raw predictions) inside the pipeline.
"""
df = get_train_dataflow() # we don't visualize mask stuff
df.reset_state()
pred = OfflinePredictor(
PredictConfig(model=model,
session_init=get_model_loader(model_path),
input_names=['image', 'gt_boxes', 'gt_labels'],
output_names=[
'generate_{}_proposals/boxes'.format(
'fpn' if cfg.MODE_FPN else 'rpn'),
'generate_{}_proposals/scores'.format(
'fpn' if cfg.MODE_FPN else 'rpn'),
'fastrcnn_all_scores',
'output/boxes',
'output/scores',
'output/labels',
]))
if os.path.isdir(output_dir):
shutil.rmtree(output_dir)
utils.fs.mkdir_p(output_dir)
with tqdm.tqdm(total=nr_visualize) as pbar:
for idx, dp in itertools.islice(enumerate(df), nr_visualize):
# img = dp[0]
img = dp['image']
if cfg.MODE_MASK:
# gt_boxes, gt_labels, gt_masks = dp[-3:]
gt_boxes, gt_labels, gt_masks = dp['gt_boxes'], dp[
'gt_labels'], dp['gt_masks']
else:
# gt_boxes, gt_labels = dp[-2:]
gt_boxes, gt_labels = dp['gt_boxes'], dp['gt_labels']
rpn_boxes, rpn_scores, all_scores, \
final_boxes, final_scores, final_labels = pred(img, gt_boxes, gt_labels)
# draw groundtruth boxes
gt_viz = draw_annotation(img, gt_boxes, gt_labels)
# draw best proposals for each groundtruth, to show recall
proposal_viz, good_proposals_ind = draw_proposal_recall(
img, rpn_boxes, rpn_scores, gt_boxes)
# draw the scores for the above proposals
score_viz = draw_predictions(img, rpn_boxes[good_proposals_ind],
all_scores[good_proposals_ind])
results = [
DetectionResult(*args)
for args in zip(final_boxes, final_scores, final_labels,
[None] * len(final_labels))
]
final_viz = draw_final_outputs(img, results)
viz = tpviz.stack_patches(
[gt_viz, proposal_viz, score_viz, final_viz], 2, 2)
if os.environ.get('DISPLAY', None):
tpviz.interactive_imshow(viz)
cv2.imwrite("{}/{:03d}.png".format(output_dir, idx), viz)
pbar.update()