def post_train_detector_job(dataset_name,
run_name,
epochs,
import_datasets=""):
dataset_name = quote(dataset_name)
run_name = quote(run_name)
rc = RunConfig(dataset_name, run_name)
dc = DatasetConfig(dataset_name)
if rc.exists and dc.exists:
cmd = [
python_path, "training_script.py",
"--name={}".format(dataset_name),
"--experiment={}".format(run_name),
"--input_shape={}".format(rc.get('detector_resolution')),
"--train_data_dir=fjlfbwjefrlbwelrfb_man_we_need_a_better_detector_codebase",
"--batch_size={}".format(rc.get('detection_training_batch_size')),
"--image_shape={}".format(dc.get('video_resolution')),
"--epochs={}".format(epochs)
]
if import_datasets:
import_datasets = quote(import_datasets)
cmd.append("--import_datasets={}".format(import_datasets))
job_id = jm.run(cmd, "train_detector")
if job_id:
return (job_id, 202)
else:
return (NoContent, 503)
else:
return (NoContent, 404)
def post_detect_objects_job(dataset_name, run_name):
dataset_name = quote(dataset_name)
run_name = quote(run_name)
rc = RunConfig(dataset_name, run_name)
if rc.exists:
cmd = [python_path, "detect_csv.py",
"--dataset={}".format(dataset_name),
"--run={}".format(run_name),
"--res={}".format(rc.get("detector_resolution")),
"--conf={}".format(rc.get("confidence_threshold")),
"--bs={}".format(rc.get("detection_batch_size"))]
job_id = jm.run(cmd, "detect_objects")
if job_id:
return (job_id, 202)
else:
return (NoContent, 503)
else:
return (NoContent, 404)
def post_visualize_detections_job(dataset_name, run_name, confidence_threshold, coords):
dataset_name = quote(dataset_name)
run_name = quote(run_name)
rc = RunConfig(dataset_name, run_name)
dc = DatasetConfig(dataset_name)
if rc.exists and dc.exists:
cmd = [python_path, "visualize_detections.py",
"--cmd=findvids",
"--dataset={}".format(dataset_name),
"--run={}".format(run_name),
"--res={}".format(rc.get("detector_resolution")),
"--conf={}".format(confidence_threshold),
"--fps={}".format(dc.get('video_fps')),
"--coords={}".format(coords)]
job_id = jm.run(cmd, "visualize_detections")
if job_id:
return (job_id, 202)
else:
return (NoContent, 503)
else:
return (NoContent, 404)
def post_detections_to_world_coordinates_job(dataset_name, run_name,
make_videos):
dataset_name = quote(dataset_name)
run_name = quote(run_name)
rc = RunConfig(dataset_name, run_name)
dc = DatasetConfig(dataset_name)
if rc.exists and dc.exists:
cmd = [
python_path, "detections_world.py", "--cmd=findvids",
"--dataset={}".format(dataset_name), "--run={}".format(run_name),
"--make_videos={}".format(make_videos),
"--ssdres={}".format(rc.get("detector_resolution")),
"--vidres={}".format(dc.get('video_resolution')),
"--kltres={}".format(dc.get('point_track_resolution'))
]
job_id = jm.run(cmd, "detections_to_world")
if job_id:
return (job_id, 202)
else:
return (NoContent, 503)
else:
return (NoContent, 404)
def main(dataset, run, n_clips, clip_length):
dc = DatasetConfig(dataset)
rc = RunConfig(dataset, run)
mask = Masker(dataset)
classes = get_classnames(dataset)
num_classes = len(classes) + 1
calib = Calibration(dataset)
dataset_path = "{dsp}{ds}/".format(dsp=datasets_path, ds=dataset)
run_path = "{rp}{ds}_{r}/".format(rp=runs_path, ds=dataset, r=run)
# Grab a bunch of videos
vids_query = "{dsp}videos/*.mkv".format(dsp=dataset_path)
all_vids = glob(vids_query)
all_vids = [right_remove(x.split('/')[-1], '.mkv') for x in all_vids]
all_vids.sort()
vids = []
if n_clips > len(all_vids):
n_clips = len(all_vids)
if n_clips == len(all_vids):
vids = all_vids
else:
while len(vids) < n_clips:
vid = choice(all_vids)
if not vid in vids:
vids.append(vid)
print_flush(vids)
# Find out what has been run on all of these videos, what to include
include_klt = True
include_pixeldets = True
include_worlddets = True
include_worldtracks = True
klts = []
pixeldets = []
worlddets = []
worldtracks = []
# Point tracks need to be converted for faster access
vidres = dc.get('video_resolution')
kltres = dc.get('point_track_resolution')
class KLTConfig(object):
klt_x_factor = 0
klt_y_factor = 0
klt_config = KLTConfig()
klt_config.klt_x_factor = vidres[0] / kltres[0]
klt_config.klt_y_factor = vidres[1] / kltres[1]
ssdres = rc.get('detector_resolution')
x_scale = vidres[0] / ssdres[0]
y_scale = vidres[1] / ssdres[1]
colors = class_colors(num_classes)
for vid in vids:
f = get_klt_path(dataset_path, vid)
if not isfile(f):
include_klt = False
else:
klt = load(f)
klt, klt_frames = convert_klt(klt, klt_config)
pts = (klt, klt_frames, class_colors(n_cols_klts))
klts.append(pts)
f = get_pixeldet_path(run_path, vid)
if not isfile(f):
include_pixeldets = False
else:
dets = pd.read_csv(f)
pixeldets.append((dets, colors, x_scale, y_scale))
f = get_worlddet_path(run_path, vid)
if not isfile(f):
include_worlddets = False
else:
dets = pd.read_csv(f)
worlddets.append((dets, colors, calib))
f = get_worldtracks_path(run_path, vid)
if not isfile(f):
include_worldtracks = False
else:
tracks = load(f)
worldtracks.append((tracks, class_colors(n_cols_tracks), calib))
print_flush("Point tracks: {}".format(include_klt))
print_flush("Pixel coordinate detections: {}".format(include_pixeldets))
print_flush("World coordinate detections: {}".format(include_worlddets))
print_flush("World coordinate tracks: {}".format(include_worldtracks))
# Decide where to start and stop in the videos
clip_length = clip_length * dc.get(
'video_fps') # convert from seconds to frames
print_flush("Clip length in frames: {}".format(clip_length))
clips = []
for vid in vids:
start, stop = make_clip(vid, clip_length, dataset_path)
clips.append((start, stop))
incs = [
include_klt, include_pixeldets, include_worlddets, include_worldtracks
]
funs = [klt_frame, pixeldet_frame, worlddet_frame, worldtracks_frame]
dats = [klts, pixeldets, worlddets, worldtracks]
nams = [
"Point tracks", "Detections in pixel coordinates",
"Detections in world coordinates", "Tracks in world coordinates"
]
print_flush(clips)
with iio.get_writer("{trp}summary.mp4".format(trp=run_path),
fps=dc.get('video_fps')) as outvid:
for i_vid, vid in enumerate(vids):
print_flush(vid)
old_prog = 0
with iio.get_reader("{dsp}videos/{v}.mkv".format(dsp=dataset_path,
v=vid)) as invid:
start, stop = clips[i_vid]
for i_frame in range(start, stop):
frame = invid.get_data(i_frame)
pieces = []
for inc, fun, dat, nam in zip(incs, funs, dats, nams):
if inc:
piece = fun(dat[i_vid],
mask.mask(frame.copy(), alpha=0.5),
i_frame)
draw_text(piece, vid, i_frame, nam)
pieces.append(piece)
outvid.append_data(join(pieces))
prog = float(i_frame - start) / (stop - start)
if prog - old_prog > 0.1:
print_flush("{}%".format(round(prog * 100)))
old_prog = prog
print_flush("Done!")