def GetPoseandCostsF(cfg, dlc_cfg, sess, inputs, outputs, cap, nframes,
batchsize, c_engine):
""" Batchwise prediction of pose """
strwidth = int(np.ceil(np.log10(nframes))) # width for strings
batch_ind = 0 # keeps track of which image within a batch should be written to
batch_num = 0 # keeps track of which batch you are at
ny, nx = int(cap.get(4)), int(cap.get(3))
if cfg["cropping"]:
print(
"Cropping based on the x1 = %s x2 = %s y1 = %s y2 = %s. You can adjust the cropping coordinates in the config.yaml file."
% (cfg["x1"], cfg["x2"], cfg["y1"], cfg["y2"]))
nx = cfg["x2"] - cfg["x1"]
ny = cfg["y2"] - cfg["y1"]
if nx > 0 and ny > 0:
pass
else:
raise Exception("Please check the order of cropping parameter!")
if (cfg["x1"] >= 0 and cfg["x2"] < int(cap.get(3) + 1)
and cfg["y1"] >= 0 and cfg["y2"] < int(cap.get(4) + 1)):
pass # good cropping box
else:
raise Exception("Please check the boundary of cropping!")
frames = np.empty((batchsize, ny, nx, 3),
dtype="ubyte") # this keeps all frames in a batch
pbar = tqdm(total=nframes)
counter = 0
step = max(10, int(nframes / 100))
PredicteData = {}
# initializing constants
dist_grid = predict.make_nms_grid(dlc_cfg.nmsradius)
stride, halfstride = dlc_cfg.stride, dlc_cfg.stride * 0.5
num_joints = dlc_cfg.num_joints
det_min_score = dlc_cfg.minconfidence
num_idchannel = dlc_cfg.get("num_idchannel", 0)
while cap.isOpened():
if counter % step == 0:
pbar.update(step)
ret, frame = cap.read()
if ret:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if cfg["cropping"]:
frames[batch_ind] = img_as_ubyte(frame[cfg["y1"]:cfg["y2"],
cfg["x1"]:cfg["x2"]])
else:
frames[batch_ind] = img_as_ubyte(frame)
if batch_ind == batchsize - 1:
# PredicteData['frame'+str(counter)]=predict.get_detectionswithcosts(frame, dlc_cfg, sess, inputs, outputs, outall=False,nms_radius=dlc_cfg.nmsradius,det_min_score=dlc_cfg.minconfidence)
D = predict.get_batchdetectionswithcosts(
frames,
dlc_cfg,
dist_grid,
batchsize,
num_joints,
num_idchannel,
stride,
halfstride,
det_min_score,
sess,
inputs,
outputs,
)
for l in range(batchsize):
# pose = predict.getposeNP(frames,dlc_cfg, sess, inputs, outputs)
# PredicteData[batch_num*batchsize:(batch_num+1)*batchsize, :] = pose
PredicteData["frame" + str(batch_num * batchsize +
l).zfill(strwidth)] = D[l]
batch_ind = 0
batch_num += 1
else:
batch_ind += 1
else:
nframes = counter
print("Detected frames: ", nframes)
if batch_ind > 0:
# pose = predict.getposeNP(frames, dlc_cfg, sess, inputs, outputs) #process the whole batch (some frames might be from previous batch!)
# PredicteData[batch_num*batchsize:batch_num*batchsize+batch_ind, :] = pose[:batch_ind,:]
D = predict.get_batchdetectionswithcosts(
frames,
dlc_cfg,
dist_grid,
batchsize,
num_joints,
num_idchannel,
stride,
halfstride,
det_min_score,
sess,
inputs,
outputs,
c_engine=c_engine,
)
for l in range(batch_ind):
# pose = predict.getposeNP(frames,dlc_cfg, sess, inputs, outputs)
# PredicteData[batch_num*batchsize:(batch_num+1)*batchsize, :] = pose
PredicteData["frame" + str(batch_num * batchsize +
l).zfill(strwidth)] = D[l]
break
counter += 1
pbar.close()
PredicteData["metadata"] = {
"nms radius":
dlc_cfg.nmsradius,
"minimal confidence":
dlc_cfg.minconfidence,
"PAFgraph":
dlc_cfg.partaffinityfield_graph,
"all_joints": [[i] for i in range(len(dlc_cfg.all_joints))],
"all_joints_names":
[dlc_cfg.all_joints_names[i] for i in range(len(dlc_cfg.all_joints))],
"nframes":
nframes,
"c_engine":
c_engine,
}
return PredicteData, nframes
def GetPoseandCostsF(cfg, dlc_cfg, sess, inputs, outputs, cap, nframes,
batchsize, c_engine):
""" Batchwise prediction of pose """
strwidth = int(np.ceil(np.log10(nframes))) # width for strings
batch_ind = 0 # keeps track of which image within a batch should be written to
batch_num = 0 # keeps track of which batch you are at
if cfg["cropping"]:
cap.set_bbox(cfg["x1"], cfg["x2"], cfg["y1"], cfg["y2"])
nx, ny = cap.dimensions
frames = np.empty((batchsize, ny, nx, 3),
dtype="ubyte") # this keeps all frames in a batch
pbar = tqdm(total=nframes)
counter = 0
step = max(10, int(nframes / 100))
inds = []
PredicteData = {}
# initializing constants
dist_grid = predict.make_nms_grid(dlc_cfg['nmsradius'])
stride = dlc_cfg['stride']
halfstride = stride * 0.5
num_joints = dlc_cfg['num_joints']
det_min_score = dlc_cfg['minconfidence']
num_idchannel = dlc_cfg.get("num_idchannel", 0)
while cap.video.isOpened():
if counter % step == 0:
pbar.update(step)
frame = cap.read_frame(crop=cfg["cropping"])
if frame is not None:
frames[batch_ind] = img_as_ubyte(frame)
inds.append(counter)
if batch_ind == batchsize - 1:
# PredicteData['frame'+str(counter)]=predict.get_detectionswithcosts(frame, dlc_cfg, sess, inputs, outputs, outall=False,nms_radius=dlc_cfg.nmsradius,det_min_score=dlc_cfg.minconfidence)
D = predict.get_batchdetectionswithcosts(
frames,
dlc_cfg,
dist_grid,
batchsize,
num_joints,
num_idchannel,
stride,
halfstride,
det_min_score,
sess,
inputs,
outputs,
)
for ind, data in zip(inds, D):
PredicteData["frame" + str(ind).zfill(strwidth)] = data
batch_ind = 0
inds.clear()
batch_num += 1
else:
batch_ind += 1
elif counter >= nframes:
if batch_ind > 0:
# pose = predict.getposeNP(frames, dlc_cfg, sess, inputs, outputs) #process the whole batch (some frames might be from previous batch!)
# PredicteData[batch_num*batchsize:batch_num*batchsize+batch_ind, :] = pose[:batch_ind,:]
D = predict.get_batchdetectionswithcosts(
frames,
dlc_cfg,
dist_grid,
batchsize,
num_joints,
num_idchannel,
stride,
halfstride,
det_min_score,
sess,
inputs,
outputs,
c_engine=c_engine,
)
for ind, data in zip(inds, D):
PredicteData["frame" + str(ind).zfill(strwidth)] = data
break
counter += 1
cap.close()
pbar.close()
PredicteData["metadata"] = {
"nms radius":
dlc_cfg['nmsradius'],
"minimal confidence":
dlc_cfg['minconfidence'],
"PAFgraph":
dlc_cfg['partaffinityfield_graph'],
"all_joints": [[i] for i in range(len(dlc_cfg['all_joints']))],
"all_joints_names": [
dlc_cfg['all_joints_names'][i]
for i in range(len(dlc_cfg['all_joints']))
],
"nframes":
nframes,
"c_engine":
c_engine,
}
return PredicteData, nframes
def GetPoseandCostsF(cfg, dlc_cfg, sess, inputs, outputs, cap, nframes,
batchsize, c_engine):
""" Batchwise prediction of pose """
strwidth = int(np.ceil(np.log10(nframes))) # width for strings
batch_ind = 0 # keeps track of which image within a batch should be written to
batch_num = 0 # keeps track of which batch you are at
if cfg["cropping"]:
cap.set_bbox(cfg["x1"], cfg["x2"], cfg["y1"], cfg["y2"])
nx, ny = cap.dimensions
frames = np.empty((batchsize, ny, nx, 3),
dtype="ubyte") # this keeps all frames in a batch
pbar = tqdm(total=nframes)
counter = 0
step = max(10, int(nframes / 100))
PredicteData = {}
# initializing constants
dist_grid = predict.make_nms_grid(dlc_cfg.nmsradius)
stride, halfstride = dlc_cfg.stride, dlc_cfg.stride * 0.5
num_joints = dlc_cfg.num_joints
det_min_score = dlc_cfg.minconfidence
num_idchannel = dlc_cfg.get("num_idchannel", 0)
# TODO Fix the code below...
# We can't just break the whole thing if there is one corrupted frame
# in the middle of the video. Rather iterate over all frames and simply skip corruptions
while cap.video.isOpened():
if counter % step == 0:
pbar.update(step)
frame = cap.read_frame(crop=cfg["cropping"])
if frame is not None:
frames[batch_ind] = img_as_ubyte(frame)
if batch_ind == batchsize - 1:
# PredicteData['frame'+str(counter)]=predict.get_detectionswithcosts(frame, dlc_cfg, sess, inputs, outputs, outall=False,nms_radius=dlc_cfg.nmsradius,det_min_score=dlc_cfg.minconfidence)
D = predict.get_batchdetectionswithcosts(
frames,
dlc_cfg,
dist_grid,
batchsize,
num_joints,
num_idchannel,
stride,
halfstride,
det_min_score,
sess,
inputs,
outputs,
)
for l in range(batchsize):
# pose = predict.getposeNP(frames,dlc_cfg, sess, inputs, outputs)
# PredicteData[batch_num*batchsize:(batch_num+1)*batchsize, :] = pose
PredicteData["frame" + str(batch_num * batchsize +
l).zfill(strwidth)] = D[l]
batch_ind = 0
batch_num += 1
else:
batch_ind += 1
else:
nframes = counter
print("Detected frames: ", nframes)
if batch_ind > 0:
# pose = predict.getposeNP(frames, dlc_cfg, sess, inputs, outputs) #process the whole batch (some frames might be from previous batch!)
# PredicteData[batch_num*batchsize:batch_num*batchsize+batch_ind, :] = pose[:batch_ind,:]
D = predict.get_batchdetectionswithcosts(
frames,
dlc_cfg,
dist_grid,
batchsize,
num_joints,
num_idchannel,
stride,
halfstride,
det_min_score,
sess,
inputs,
outputs,
c_engine=c_engine,
)
for l in range(batch_ind):
# pose = predict.getposeNP(frames,dlc_cfg, sess, inputs, outputs)
# PredicteData[batch_num*batchsize:(batch_num+1)*batchsize, :] = pose
PredicteData["frame" + str(batch_num * batchsize +
l).zfill(strwidth)] = D[l]
break
counter += 1
cap.close()
pbar.close()
PredicteData["metadata"] = {
"nms radius":
dlc_cfg.nmsradius,
"minimal confidence":
dlc_cfg.minconfidence,
"PAFgraph":
dlc_cfg.partaffinityfield_graph,
"all_joints": [[i] for i in range(len(dlc_cfg.all_joints))],
"all_joints_names":
[dlc_cfg.all_joints_names[i] for i in range(len(dlc_cfg.all_joints))],
"nframes":
nframes,
"c_engine":
c_engine,
}
return PredicteData, nframes