def det_process(opts, frame_recv, det_res_send, w_img, h_img):
try:
model = init_detector(opts)
# warm up the GPU
_ = inference_detector(model, np.zeros((h_img, w_img, 3), np.uint8))
torch.cuda.synchronize()
while 1:
fidx = frame_recv.recv()
if type(fidx) is list:
# new video, read all images in advance
frame_list = fidx
frames = [imread(img_path) for img_path in frame_list]
# signal ready, no errors
det_res_send.send('ready')
continue
elif fidx is None:
# exit flag
break
fidx, t1 = fidx
img = frames[fidx]
t2 = perf_counter()
t_send_frame = t2 - t1
result = inference_detector(model, img, gpu_pre=not opts.cpu_pre)
torch.cuda.synchronize()
t3 = perf_counter()
det_res_send.send([result, t_send_frame, t3])
except Exception:
# report all errors from the child process to the parent
# forward traceback info as well
det_res_send.send(Exception("".join(traceback.format_exception(*sys.exc_info()))))
def det_test(opts, scale, imgs):
assert len(imgs)
opts.in_scale = scale
opts.no_mask = True
model = init_detector(opts)
# warm up the GPU
_ = inference_detector(model, imgs[0])
torch.cuda.synchronize()
runtime = []
for img in imgs:
t1 = perf_counter()
_ = inference_detector(model, img, gpu_pre=not opts.cpu_pre)
torch.cuda.synchronize()
t2 = perf_counter()
runtime.append(t2 - t1)
return sum(runtime) / len(runtime)
def main():
assert torch.cuda.device_count(
) == 1 # mmdet only supports single GPU testing
opts = parse_args()
mkdir2(opts.out_dir)
vis_out = bool(opts.vis_dir)
if vis_out:
mkdir2(opts.vis_dir)
db = COCO(opts.annot_path)
class_names = [c['name'] for c in db.dataset['categories']]
n_class = len(class_names)
coco_mapping = None if opts.no_class_mapping else db.dataset.get(
'coco_mapping', None)
if coco_mapping is not None:
coco_mapping = np.asarray(coco_mapping)
seqs = db.dataset['sequences']
seq_dirs = db.dataset['seq_dirs']
model = init_detector(opts)
results_raw = [] # image based, all 80 COCO classes
results_ccf = [] # instance based
for iid, img in tqdm(db.imgs.items()):
img_name = img['name']
sid = img['sid']
seq_name = seqs[sid]
img_path = join(opts.data_root, seq_dirs[sid], img_name)
I = imread(img_path)
result = inference_detector(model, I, gpu_pre=not opts.cpu_pre)
results_raw.append(result)
bboxes, scores, labels, masks = \
parse_det_result(result, coco_mapping, n_class)
if vis_out:
vis_path = join(opts.vis_dir, seq_name, img_name[:-3] + 'jpg')
if opts.overwrite or not isfile(vis_path):
vis_det(I,
bboxes,
labels,
class_names,
masks,
scores,
out_scale=opts.vis_scale,
out_file=vis_path)
# convert to coco fmt
n = len(bboxes)
if n:
ltrb2ltwh_(bboxes)
for i in range(n):
result_dict = {
'image_id': iid,
'bbox': bboxes[i],
'score': scores[i],
'category_id': labels[i],
}
if masks is not None:
result_dict['segmentation'] = masks[i]
results_ccf.append(result_dict)
out_path = join(opts.out_dir, 'results_raw.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump(results_raw, open(out_path, 'wb'))
out_path = join(opts.out_dir, 'results_ccf.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump(results_ccf, open(out_path, 'wb'))
if not opts.no_eval:
eval_summary = eval_ccf(db, results_ccf)
out_path = join(opts.out_dir, 'eval_summary.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump(eval_summary, open(out_path, 'wb'))
if opts.eval_mask:
print('Evaluating instance segmentation')
eval_summary = eval_ccf(db, results_ccf, iou_type='segm')
out_path = join(opts.out_dir, 'eval_summary_mask.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump(eval_summary, open(out_path, 'wb'))
if vis_out:
print(f'python vis/make_videos.py "{opts.vis_dir}"')
def main():
assert torch.cuda.device_count() == 1 # mmdet only supports single GPU testing
opts = parse_args()
assert (not opts.mask_timing) or (opts.mask_timing and not opts.no_mask)
mkdir2(opts.out_dir)
db = COCO(opts.annot_path)
class_names = [c['name'] for c in db.dataset['categories']]
n_class = len(class_names)
coco_mapping = None if opts.no_class_mapping else db.dataset.get('coco_mapping', None)
if coco_mapping is not None:
coco_mapping = np.asarray(coco_mapping)
seqs = db.dataset['sequences']
seq_dirs = db.dataset['seq_dirs']
model = init_detector(opts)
# warm up the GPU
img = db.imgs[0]
w_img, h_img = img['width'], img['height']
_ = inference_detector(model, np.zeros((h_img, w_img, 3), np.uint8))
torch.cuda.synchronize()
runtime_all = []
n_processed = 0
n_total = 0
for sid, seq in enumerate(tqdm(seqs)):
frame_list = [img for img in db.imgs.values() if img['sid'] == sid]
# load all frames in advance
frames = []
for img in frame_list:
img_path = join(opts.data_root, seq_dirs[sid], img['name'])
frames.append(imread(img_path))
n_frame = len(frames)
n_total += n_frame
timestamps = []
results_raw = []
results_parsed = []
input_fidx = []
runtime = []
last_fidx = None
if not opts.dynamic_schedule:
stride_cnt = 0
t_total = n_frame/opts.fps
t_start = perf_counter()
while 1:
t1 = perf_counter()
t_elapsed = t1 - t_start
if t_elapsed >= t_total:
break
# identify latest available frame
fidx_continous = t_elapsed*opts.fps
fidx = int(np.floor(fidx_continous))
if fidx == last_fidx:
continue
last_fidx = fidx
if opts.dynamic_schedule:
fidx_remainder = fidx_continous - fidx
if fidx_remainder > 0.5:
continue
else:
if stride_cnt % opts.det_stride == 0:
stride_cnt = 1
else:
stride_cnt += 1
continue
frame = frames[fidx]
result = inference_detector(model, frame, gpu_pre=not opts.cpu_pre, decode_mask=not opts.mask_timing)
if opts.mask_timing:
mask_encoded = result[2]
result = result[:2]
bboxes, scores, labels, _, sel = \
parse_det_result(result, coco_mapping, n_class, return_sel=True)
else:
bboxes, scores, labels, masks = \
parse_det_result(result, coco_mapping, n_class)
torch.cuda.synchronize()
t2 = perf_counter()
t_elapsed = t2 - t_start
if t_elapsed >= t_total:
break
if opts.mask_timing:
masks = decode_mask(mask_encoded, sel)
timestamps.append(t_elapsed)
results_raw.append(result)
results_parsed.append((bboxes, scores, labels, masks))
input_fidx.append(fidx)
runtime.append(t2 - t1)
out_path = join(opts.out_dir, seq + '.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump({
'results_raw': results_raw,
'results_parsed': results_parsed,
'timestamps': timestamps,
'input_fidx': input_fidx,
'runtime': runtime,
}, open(out_path, 'wb'))
runtime_all += runtime
n_processed += len(results_raw)
runtime_all_np = np.asarray(runtime_all)
n_small_runtime = (runtime_all_np < 1.0/opts.fps).sum()
out_path = join(opts.out_dir, 'time_info.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump({
'runtime_all': runtime_all,
'n_processed': n_processed,
'n_total': n_total,
'n_small_runtime': n_small_runtime,
}, open(out_path, 'wb'))
# convert to ms for display
s2ms = lambda x: 1e3*x
print(f'{n_processed}/{n_total} frames processed')
print_stats(runtime_all_np, 'Runtime (ms)', cvt=s2ms)
print(f'Runtime smaller than unit time interval: '
f'{n_small_runtime}/{n_processed} '
f'({100.0*n_small_runtime/n_processed:.4g}%)')
def main():
opts = parse_args()
mkdir2(opts.out_dir)
db = COCO(opts.annot_path)
class_names = [c['name'] for c in db.dataset['categories']]
n_class = len(class_names)
coco_mapping = None if opts.no_class_mapping else db.dataset.get('coco_mapping', None)
if coco_mapping is not None:
coco_mapping = np.asarray(coco_mapping)
seqs = db.dataset['sequences']
seq_dirs = db.dataset['seq_dirs']
if opts.cached_res:
cache_in_ccf = '_ccf' in basename(opts.cached_res)
if cache_in_ccf:
# speed up based on the assumption of sequential storage
cache_end_idx = 0
cached_res = pickle.load(open(opts.cached_res, 'rb'))
else:
assert torch.cuda.device_count() == 1 # mmdet only supports single GPU testing
model = init_detector(opts)
np.random.seed(opts.seed)
runtime = pickle.load(open(opts.runtime, 'rb'))
runtime_dist = dist_from_dict(runtime, opts.perf_factor)
runtime_all = []
n_processed = 0
n_total = 0
for sid, seq in enumerate(tqdm(seqs)):
frame_list = [img for img in db.imgs.values() if img['sid'] == sid]
n_frame = len(frame_list)
n_total += n_frame
if not opts.cached_res:
# load all frames in advance
frames = []
for img in frame_list:
img_path = join(opts.data_root, seq_dirs[sid], img['name'])
frames.append(imread(img_path))
timestamps = []
results_parsed = []
input_fidx = []
runtime = []
last_fidx = None
if opts.cached_res and cache_in_ccf:
results_raw = None
else:
results_raw = []
t_total = n_frame/opts.fps
t_elapsed = 0
if opts.dynamic_schedule:
mean_rtf = runtime_dist.mean()*opts.fps
else:
stride_cnt = 0
while 1:
if t_elapsed >= t_total:
break
# identify latest available frame
fidx_continous = t_elapsed*opts.fps
fidx = int(np.floor(fidx_continous))
if fidx == last_fidx:
# algorithm is fast and has some idle time
fidx += 1
if fidx == n_frame:
break
t_elapsed = fidx/opts.fps
last_fidx = fidx
if opts.dynamic_schedule:
if mean_rtf > 1:
# when runtime <= 1, it should always process every frame
fidx_remainder = fidx_continous - fidx
if mean_rtf < np.floor(fidx_remainder + mean_rtf):
# wait till next frame
continue
else:
if stride_cnt % opts.det_stride == 0:
stride_cnt = 1
else:
stride_cnt += 1
continue
if opts.cached_res:
img = frame_list[fidx]
if cache_in_ccf:
cache_end_idx, bboxes, scores, labels, masks = \
result_from_ccf(cached_res, img['id'], cache_end_idx)
ltwh2ltrb_(bboxes)
else:
result = cached_res[img['id']]
bboxes, scores, labels, masks = \
parse_det_result(result, coco_mapping, n_class)
else:
frame = frames[fidx]
result = inference_detector(model, frame)
bboxes, scores, labels, masks = \
parse_det_result(result, coco_mapping, n_class)
rt_this = runtime_dist.draw()
t_elapsed += rt_this
if t_elapsed >= t_total:
break
timestamps.append(t_elapsed)
if results_raw is not None:
results_raw.append(result)
results_parsed.append((bboxes, scores, labels, masks))
input_fidx.append(fidx)
runtime.append(rt_this)
out_path = join(opts.out_dir, seq + '.pkl')
if opts.overwrite or not isfile(out_path):
out_dict = {
'results_parsed': results_parsed,
'timestamps': timestamps,
'input_fidx': input_fidx,
'runtime': runtime,
}
if results_raw is not None:
out_dict['results_raw'] = results_raw
pickle.dump(out_dict, open(out_path, 'wb'))
runtime_all += runtime
n_processed += len(results_parsed)
runtime_all_np = np.array(runtime_all)
n_small_runtime = (runtime_all_np < 1.0/opts.fps).sum()
out_path = join(opts.out_dir, 'time_info.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump({
'runtime_all': runtime_all,
'n_processed': n_processed,
'n_total': n_total,
'n_small_runtime': n_small_runtime,
}, open(out_path, 'wb'))
# convert to ms for display
s2ms = lambda x: 1e3*x
print(f'{n_processed}/{n_total} frames processed')
print_stats(runtime_all_np, 'Runtime (ms)', cvt=s2ms)
print(f'Runtime smaller than unit time interval: '
f'{n_small_runtime}/{n_processed} '
f'({100.0*n_small_runtime/n_processed:.4g}%)')
def main():
assert torch.cuda.device_count(
) == 1 # mmdet only supports single GPU testing
opts = parse_args()
mkdir2(opts.out_dir)
db = COCO(opts.annot_path)
class_names = [c['name'] for c in db.dataset['categories']]
n_class = len(class_names)
coco_mapping = db.dataset.get('coco_mapping', None)
if coco_mapping is not None:
coco_mapping = np.asarray(coco_mapping)
seqs = db.dataset['sequences']
seq_dirs = db.dataset['seq_dirs']
model = init_detector(opts)
# warm up the GPU
img = db.imgs[0]
w_img, h_img = img['width'], img['height']
_ = inference_detector(model, np.zeros((h_img, w_img, 3), np.uint8))
torch.cuda.synchronize()
runtime_all = []
n_processed = 0
n_total = 0
# global pr
import cProfile
pr = cProfile.Profile()
for sid, seq in enumerate(tqdm(seqs)):
# if sid > 1:
# break
frame_list = [img for img in db.imgs.values() if img['sid'] == sid]
# load all frames in advance
frames = []
for img in frame_list:
img_path = join(opts.data_root, seq_dirs[sid], img['name'])
frames.append(imread(img_path))
n_frame = len(frames)
n_total += n_frame
timestamps = []
results = []
input_fidx = []
runtime = []
last_fidx = None
t_total = n_frame / opts.fps
t_start = perf_counter()
while 1:
t1 = perf_counter()
t_elapsed = t1 - t_start
if t_elapsed >= t_total:
break
# identify latest available frame
fidx = int(np.floor(t_elapsed * opts.fps))
# t_elapsed/t_total *n_frame
# = t_elapsed*opts.fps
if fidx == last_fidx:
continue
last_fidx = fidx
frame = frames[fidx]
pr.enable()
result = inference_detector(model, frame)
torch.cuda.synchronize()
pr.disable()
t2 = perf_counter()
t_elapsed = t2 - t_start
if t_elapsed >= t_total:
break
timestamps.append(t_elapsed)
results.append(result)
input_fidx.append(fidx)
runtime.append(t2 - t1)
out_path = join(opts.out_dir, seq + '.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump((
results,
timestamps,
input_fidx,
runtime,
), open(out_path, 'wb'))
runtime_all += runtime
n_processed += len(results)
pr.dump_stats('_par_/mrcnn50_s0.5_1080ti_gpupre_blocking.prof')
# pr.dump_stats('debug.prof')
runtime_all_np = np.array(runtime_all)
n_small_runtime = (runtime_all_np < 1.0 / opts.fps).sum()
out_path = join(opts.out_dir, 'time_info.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump(
{
'runtime_all': runtime_all,
'n_processed': n_processed,
'n_total': n_total,
'n_small_runtime': n_small_runtime,
}, open(out_path, 'wb'))
# convert to ms for display
runtime_all_np *= 1e3
print(f'{n_processed}/{n_total} frames processed')
print('Runtime (ms): mean: %g; std: %g; min: %g; max: %g' % (
runtime_all_np.mean(),
runtime_all_np.std(ddof=1),
runtime_all_np.min(),
runtime_all_np.max(),
))
print(f'Runtime smaller than unit time interval: '
f'{n_small_runtime}/{n_processed} '
f'({100.0*n_small_runtime/n_processed:.4g}%)')
def main():
opts = parse_args()
mkdir2(opts.out_dir)
db = COCO(opts.annot_path)
class_names = [c['name'] for c in db.dataset['categories']]
n_class = len(class_names)
coco_mapping = db.dataset.get('coco_mapping', None)
if coco_mapping is not None:
coco_mapping = np.asarray(coco_mapping)
seqs = db.dataset['sequences']
seq_dirs = db.dataset['seq_dirs']
if opts.cached_res:
cache_in_ccf = '_ccf' in basename(opts.cached_res)
if cache_in_ccf:
# speed up based on the assumption of sequential storage
cache_end_idx = 0
cached_res = pickle.load(open(opts.cached_res, 'rb'))
else:
assert torch.cuda.device_count(
) == 1 # mmdet only supports single GPU testing
model = init_detector(opts)
np.random.seed(opts.seed)
runtime = pickle.load(open(opts.runtime, 'rb'))
runtime_dist = dist_from_dict(runtime, opts.perf_factor)
runtime_all = []
n_processed = 0
n_total = 0
for sid, seq in enumerate(tqdm(seqs)):
frame_list = [img for img in db.imgs.values() if img['sid'] == sid]
n_frame = len(frame_list)
n_total += n_frame
if not opts.cached_res:
# load all frames in advance
frames = []
for img in frame_list:
img_path = join(opts.data_root, seq_dirs[sid], img['name'])
frames.append(imread(img_path))
timestamps = []
results_raw = []
results_parsed = []
input_fidx = []
runtime = []
if opts.cached_res and cache_in_ccf:
results_raw = None
else:
results_raw = []
for ii in range(n_frame):
t = ii / opts.fps
if opts.cached_res:
img = frame_list[ii]
if cache_in_ccf:
cache_end_idx, bboxes, scores, labels, masks = \
result_from_ccf(cached_res, img['id'], cache_end_idx)
ltwh2ltrb_(bboxes)
else:
result = cached_res[img['id']]
bboxes, scores, labels, masks = \
parse_det_result(result, coco_mapping, n_class)
else:
frame = frames[ii]
result = inference_detector(model, frame)
bboxes, scores, labels, masks = \
parse_det_result(result, coco_mapping, n_class)
rt_this = runtime_dist.draw()
t_finishing = t + rt_this
timestamps.append(t_finishing)
if results_raw is not None:
results_raw.append(result)
results_parsed.append((bboxes, scores, labels, masks))
input_fidx.append(ii)
runtime.append(rt_this)
# since parallel excecution, the order is not guaranteed
idx = np.argsort(timestamps)
timestamps = [timestamps[i] for i in idx]
if results_raw is not None:
results_raw = [results_raw[i] for i in idx]
results_parsed = [results_parsed[i] for i in idx]
input_fidx = [input_fidx[i] for i in idx]
runtime = [runtime[i] for i in idx]
out_path = join(opts.out_dir, seq + '.pkl')
if opts.overwrite or not isfile(out_path):
out_dict = {
'results_parsed': results_parsed,
'timestamps': timestamps,
'input_fidx': input_fidx,
'runtime': runtime,
}
if results_raw is not None:
out_dict['results_raw'] = results_raw
pickle.dump(out_dict, open(out_path, 'wb'))
runtime_all += runtime
n_processed += len(results_parsed)
runtime_all_np = np.array(runtime_all)
n_small_runtime = (runtime_all_np < 1.0 / opts.fps).sum()
out_path = join(opts.out_dir, 'time_info.pkl')
if opts.overwrite or not isfile(out_path):
pickle.dump(
{
'runtime_all': runtime_all,
'n_processed': n_processed,
'n_total': n_total,
'n_small_runtime': n_small_runtime,
}, open(out_path, 'wb'))
# convert to ms for display
s2ms = lambda x: 1e3 * x
print(f'{n_processed}/{n_total} frames processed')
print_stats(runtime_all_np, 'Runtime (ms)', cvt=s2ms)
print(f'Runtime smaller than unit time interval: '
f'{n_small_runtime}/{n_processed} '
f'({100.0*n_small_runtime/n_processed:.4g}%)')