def main_IE_infer():
fps = ""
framepos = 0
frame_count = 0
vidfps = 0
skip_frame = 0
elapsedTime = 0
args = build_argparser().parse_args()
result_file = args.result
model_xml = args.model
test_dir = args.test_dir
model_bin = os.path.splitext(model_xml)[0] + ".bin"
time.sleep(1)
plugin = IEPlugin(device=args.device)
if "CPU" in args.device:
print('executing in cpu')
plugin.add_cpu_extension("lib/libcpu_extension.so")
net = IENetwork(model=model_xml, weights=model_bin)
input_blob = next(iter(net.inputs))
exec_net = plugin.load(network=net)
counter = 0
images = glob.glob(test_dir + '/*.jpg')
print('Num images', len(images))
from PIL import Image
results = []
for item in images:
t1 = time.time()
image = np.asarray(Image.open(item).convert('RGB'))
master = np.zeros((1920, 1920, 3), dtype='uint8')
master[420:1500, :] = image
image = master
camera_height, camera_width = image.shape[0:2]
new_w, new_h = 416, 416
resized_image = cv2.resize(image, (new_w, new_h),
interpolation=cv2.INTER_CUBIC)
canvas = np.full((m_input_size, m_input_size, 3), 0)
canvas[(m_input_size - new_h) // 2:(m_input_size - new_h) // 2 + new_h,
(m_input_size - new_w) // 2:(m_input_size - new_w) // 2 +
new_w, :] = resized_image
prepimg = canvas
prepimg = prepimg[np.newaxis, :, :, :] # Batch size axis add
prepimg = prepimg.transpose((0, 3, 1, 2)) # NHWC to NCHW
#print (prepimg.shape)
outputs = exec_net.infer(inputs={input_blob: prepimg})
objects = []
for output in outputs.values():
objects = ParseYOLOV3Output(output, new_h, new_w, camera_height,
camera_width, 0.5, objects)
# Filtering overlapping boxes
objlen = len(objects)
for i in range(objlen):
if (objects[i].confidence == 0.0):
continue
for j in range(i + 1, objlen):
if (IntersectionOverUnion(objects[i], objects[j]) >= 0.5):
objects[j].confidence = 0
# Save detection
for obj in objects:
if obj.confidence < 0.5:
continue
label = obj.class_id
confidence = obj.confidence
if confidence > 0.5:
xmin, ymin, xmax, ymax = obj.xmin, obj.ymin - 420, obj.xmax, obj.ymax - 420
x, y, w, h = xmin, ymin, xmax - xmin, ymax - ymin
anns = {
'image_id': item.split('/')[-1].replace('.jpg', ''),
'category_id': 1,
'segmentation': [],
'area': float(w * h),
'bbox': [x, y, w, h],
'score': float(confidence),
'iscrowd': 0
}
results.append(anns)
elapsedTime = time.time() - t1
fps = "(Playback) {:.1f} FPS".format(1 / elapsedTime)
print(fps)
json.dump(results, open(result_file, 'w'))
del net
del exec_net
del plugin
def main_IE_infer():
# camera_width = 416
# camera_height = 416
camera_width = 300
camera_height = 300
fps = ""
framepos = 0
frame_count = 0
vidfps = 0
skip_frame = 0
elapsedTime = 0
new_w = int(camera_width * m_input_size / camera_width)
new_h = int(camera_height * m_input_size / camera_height)
args = build_argparser().parse_args()
#model_xml = "lrmodels/tiny-YoloV3/FP32/frozen_tiny_yolo_v3.xml" #<--- CPU
#model_xml = "lrmodels/tiny-YoloV3/FP16/frozen_tiny_yolo_v3.xml" #<--- MYRIAD
model_xml = "/home/pi/openvino/rtdetection/models/mobilenet-ssd/FP16/mobilenet-ssd.xml" #<--- MYRIAD
model_bin = os.path.splitext(model_xml)[0] + ".bin"
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FPS, 30)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, camera_width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, camera_height)
#pdb.set_trace()
#cap = cv2.VideoCapture("data/input/testvideo.mp4")
#camera_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
#camera_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
#frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
#vidfps = int(cap.get(cv2.CAP_PROP_FPS))
#print("videosFrameCount =", str(frame_count))
#print("videosFPS =", str(vidfps))
time.sleep(1)
plugin = IEPlugin(device=args.device)
if "CPU" in args.device:
plugin.add_cpu_extension("lib/libcpu_extension.so")
net = IENetwork(model=model_xml, weights=model_bin)
input_blob = next(iter(net.inputs))
exec_net = plugin.load(network=net)
while cap.isOpened():
t1 = time.time()
## Uncomment only when playing video files
#cap.set(cv2.CAP_PROP_POS_FRAMES, framepos)
ret, image = cap.read()
if not ret:
break
#pdb.set_trace()
#resized_image = cv2.resize(image, (new_w, new_h), interpolation = cv2.INTER_CUBIC)
resized_image = image
canvas = np.full((m_input_size, m_input_size, 3), 128)
canvas[(m_input_size - new_h) // 2:(m_input_size - new_h) // 2 + new_h,
(m_input_size - new_w) // 2:(m_input_size - new_w) // 2 +
new_w, :] = resized_image
prepimg = canvas
prepimg = prepimg[np.newaxis, :, :, :] # Batch size axis add
prepimg = prepimg.transpose((0, 3, 1, 2)) # NHWC to NCHW
outputs = exec_net.infer(inputs={input_blob: prepimg})
#output_name = detector/yolo-v3-tiny/Conv_12/BiasAdd/YoloRegion
#output_name = detector/yolo-v3-tiny/Conv_9/BiasAdd/YoloRegion
objects = []
for output in outputs.values():
objects = ParseYOLOV3Output(output, new_h, new_w, camera_height,
camera_width, 0.4, objects)
# Filtering overlapping boxes
objlen = len(objects)
for i in range(objlen):
if (objects[i].confidence == 0.0):
continue
for j in range(i + 1, objlen):
if (IntersectionOverUnion(objects[i], objects[j]) >= 0.4):
if objects[i].confidence < objects[j].confidence:
objects[i], objects[j] = objects[j], objects[i]
objects[j].confidence = 0.0
# Drawing boxes
for obj in objects:
if obj.confidence < 0.2:
continue
label = obj.class_id
confidence = obj.confidence
#if confidence >= 0.2:
label_text = LABELS[label] + " (" + "{:.1f}".format(
confidence * 100) + "%)"
cv2.rectangle(image, (obj.xmin, obj.ymin), (obj.xmax, obj.ymax),
box_color, box_thickness)
cv2.putText(image, label_text, (obj.xmin, obj.ymin - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, label_text_color, 1)
cv2.putText(image, fps, (camera_width - 170, 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (38, 0, 255), 1,
cv2.LINE_AA)
cv2.imshow("Result", image)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
elapsedTime = time.time() - t1
fps = "(Playback) {:.1f} FPS".format(1 / elapsedTime)
## frame skip, video file only
#skip_frame = int((vidfps - int(1/elapsedTime)) / int(1/elapsedTime))
#framepos += skip_frame
cv2.destroyAllWindows()
del net
del exec_net
del plugin
def main_IE_infer():
camera_width = 320
camera_height = 240
m_input_size = 513
fps = ""
framepos = 0
frame_count = 0
vidfps = 0
skip_frame = 0
elapsedTime = 0
args = build_argparser().parse_args()
#model_xml = "lrmodels/PascalVOC/FP32/frozen_inference_graph.xml" #<--- CPU
model_xml = "lrmodels/PascalVOC/FP16/frozen_inference_graph.xml" #<--- MYRIAD
model_bin = os.path.splitext(model_xml)[0] + ".bin"
seg_image = Image.open("data/input/009649.png")
palette = seg_image.getpalette() # Get a color palette
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FPS, 10)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, camera_width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, camera_height)
#cap = cv2.VideoCapture("data/input/testvideo.mp4")
#camera_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
#camera_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
#frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
#vidfps = int(cap.get(cv2.CAP_PROP_FPS))
#print("videosFrameCount =", str(frame_count))
#print("videosFPS =", str(vidfps))
time.sleep(1)
plugin = IEPlugin(device=args.device, plugin_dirs=args.plugin_dir)
if "CPU" in args.device:
plugin.add_cpu_extension("lib/libcpu_extension.so")
if args.performance:
plugin.set_config({"PERF_COUNT": "YES"})
# Read IR
net = IENetwork(model=model_xml, weights=model_bin)
input_blob = next(iter(net.inputs))
exec_net = plugin.load(network=net)
while cap.isOpened():
t1 = time.time()
#cap.set(cv2.CAP_PROP_POS_FRAMES, framepos) # Uncomment only when playing video files
ret, image = cap.read()
if not ret:
break
ratio = 1.0 * m_input_size / max(image.shape[0], image.shape[1])
shrink_size = (int(ratio * image.shape[1]),
int(ratio * image.shape[0]))
image = cv2.resize(image, shrink_size, interpolation=cv2.INTER_CUBIC)
prepimg = _pre._pre_process(image)
prepimg = prepimg.transpose((0, 3, 1, 2)) #NHWC to NCHW
res = exec_net.infer(inputs={input_blob: prepimg})
result = _post._post_process(res["ArgMax/Squeeze"], image)[0]
outputimg = Image.fromarray(np.uint8(result), mode="P")
outputimg.putpalette(palette)
outputimg = outputimg.convert("RGB")
outputimg = np.asarray(outputimg)
outputimg = cv2.cvtColor(outputimg, cv2.COLOR_RGB2BGR)
outputimg = cv2.addWeighted(image, 1.0, outputimg, 0.9, 0)
outputimg = cv2.resize(outputimg, (camera_width, camera_height))
cv2.putText(outputimg, fps, (camera_width - 180, 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (38, 0, 255), 1,
cv2.LINE_AA)
cv2.imshow("Result", outputimg)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
elapsedTime = time.time() - t1
fps = "(Playback) {:.1f} FPS".format(1 / elapsedTime)
# frame skip, video file only
skip_frame = int(
(vidfps - int(1 / elapsedTime)) / int(1 / elapsedTime))
framepos += skip_frame
cv2.destroyAllWindows()
del net
del exec_net
del plugin
class NcsWorker(object):
def __init__(self, devid, device, model_xml, frameBuffer, results,
camera_width, camera_height, number_of_ncs, vidfps, nPoints,
w, h, new_w, new_h):
self.devid = devid
self.frameBuffer = frameBuffer
self.model_xml = model_xml
self.model_bin = os.path.splitext(model_xml)[0] + ".bin"
self.camera_width = camera_width
self.camera_height = camera_height
self.threshold = 0.1
self.nPoints = nPoints
self.num_requests = 4
self.inferred_request = [0] * self.num_requests
self.heap_request = []
self.inferred_cnt = 0
self.plugin = IEPlugin(device=device)
if "CPU" == device:
if platform.processor() == "x86_64":
self.plugin.add_cpu_extension("lib/libcpu_extension.so")
self.net = IECore().read_network(model=self.model_xml,
weights=self.model_bin)
self.input_blob = next(iter(self.net.inputs))
self.exec_net = IECore().load_network(network=self.net,
device_name=device,
num_requests=self.num_requests)
self.results = results
self.number_of_ncs = number_of_ncs
self.predict_async_time = 250
self.skip_frame = 0
self.roop_frame = 0
self.vidfps = vidfps
self.w = w #432
self.h = h #368
self.new_w = new_w
self.new_h = new_h
def skip_frame_measurement(self):
surplustime_per_second = (1000 - self.predict_async_time)
if surplustime_per_second > 0.0:
frame_per_millisecond = (1000 / self.vidfps)
total_skip_frame = surplustime_per_second / frame_per_millisecond
self.skip_frame = int(total_skip_frame / self.num_requests)
else:
self.skip_frame = 0
def predict_async(self):
try:
if self.frameBuffer.empty():
return
self.roop_frame += 1
if self.roop_frame <= self.skip_frame:
self.frameBuffer.get()
return
self.roop_frame = 0
prepimg = self.frameBuffer.get()
reqnum = searchlist(self.inferred_request, 0)
if reqnum > -1:
prepimg = prepimg[np.newaxis, :, :, :] # Batch size axis add
prepimg = prepimg.transpose(
(0, 3, 1, 2)) # NHWC to NCHW, (1, 3, 368, 432)
self.exec_net.start_async(request_id=reqnum,
inputs={self.input_blob: prepimg})
self.inferred_request[reqnum] = 1
self.inferred_cnt += 1
if self.inferred_cnt == sys.maxsize:
self.inferred_request = [0] * self.num_requests
self.heap_request = []
self.inferred_cnt = 0
heapq.heappush(self.heap_request, (self.inferred_cnt, reqnum))
try:
cnt, dev = heapq.heappop(self.heap_request)
except:
return
if self.exec_net.requests[dev].wait(0) == 0:
self.exec_net.requests[dev].wait(-1)
detected_keypoints = []
keypoints_list = np.zeros((0, 3))
keypoint_id = 0
outputs = self.exec_net.requests[dev].outputs[
"Openpose/concat_stage7"]
for part in range(self.nPoints):
probMap = outputs[0, part, :, :]
probMap = cv2.resize(probMap,
(self.w, self.h)) # (432, 368)
keypoints = getKeypoints(probMap, self.threshold)
keypoints_with_id = []
for i in range(len(keypoints)):
keypoints_with_id.append(keypoints[i] +
(keypoint_id, ))
keypoints_list = np.vstack(
[keypoints_list, keypoints[i]])
keypoint_id += 1
detected_keypoints.append(keypoints_with_id)
self.results.put([detected_keypoints, outputs, keypoints_list])
self.inferred_request[dev] = 0
else:
heapq.heappush(self.heap_request, (cnt, dev))
except:
import traceback
traceback.print_exc()
def main_IE_infer(cap):
camera_width = 640 #320
camera_height = 480 # 240
fps = ""
framepos = 0
frame_count = 0
vidfps = 0
skip_frame = 0
elapsedTime = 0
new_w = int(camera_width * m_input_size/camera_width)
new_h = int(camera_height * m_input_size/camera_height)
args = build_argparser().parse_args()
model_xml = "lrmodels/YoloV3/FP32/frozen_yolo_v3.xml" #<--- CPU
#model_xml = "lrmodels/YoloV3/FP16/frozen_yolo_v3.xml" #<--- MYRIAD
model_bin = os.path.splitext(model_xml)[0] + ".bin"
cap.set(cv2.CAP_PROP_FPS, 30)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, camera_width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, camera_height)
time.sleep(1)
plugin = IEPlugin(device=args.device)
if "CPU" in args.device:
plugin.add_cpu_extension("lib/libcpu_extension.so")
net = IENetwork(model=model_xml, weights=model_bin)
input_blob = next(iter(net.inputs))
exec_net = plugin.load(network=net)
while cap.isOpened():
t1 = int(time.time()*1000)
ret, image = cap.read()
if not ret:
continue
resized_image = cv2.resize(image, (new_w, new_h), interpolation = cv2.INTER_CUBIC)
canvas = np.full((m_input_size, m_input_size, 3), 128)
canvas[(m_input_size-new_h)//2:(m_input_size-new_h)//2 + new_h,(m_input_size-new_w)//2:(m_input_size-new_w)//2 + new_w, :] = resized_image
prepimg = canvas
prepimg = prepimg[np.newaxis, :, :, :] # Batch size axis add
prepimg = prepimg.transpose((0, 3, 1, 2)) # NHWC to NCHW
outputs = exec_net.infer(inputs={input_blob: prepimg})
objects = []
for output in outputs.values():
objects = ParseYOLOV3Output(output, new_h, new_w, camera_height, camera_width, 0.7, objects)
# Filtering overlapping boxes
objlen = len(objects)
for i in range(objlen):
if (objects[i].confidence == 0.0):
continue
for j in range(i + 1, objlen):
if (IntersectionOverUnion(objects[i], objects[j]) >= 0.4):
objects[j].confidence = 0
# Drawing boxes
for obj in objects:
if obj.confidence < 0.2:
continue
label = obj.class_id
confidence = obj.confidence
if confidence > 0.2:
label_text = LABELS[label] + " (" + "{:.1f}".format(confidence * 100) + "%)"
cv2.rectangle(image, (obj.xmin, obj.ymin), (obj.xmax, obj.ymax), box_color, box_thickness)
cv2.putText(image, label_text, (obj.xmin, obj.ymin - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, label_text_color, 1)
cv2.putText(image, fps, (camera_width - 170, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (38, 0, 255), 1, cv2.LINE_AA)
cv2.imshow("Result", image)
if cv2.waitKey(1)&0xFF == ord('q'):
break
elapsedTime = int(time.time()*1000) - t1
fps = "(Playback) {:.1f} FPS".format(1/elapsedTime)
## frame skip, video file only
#skip_frame = int((vidfps - int(1/elapsedTime)) / int(1/elapsedTime))
#framepos += skip_frame
cv2.destroyAllWindows()
del net
del exec_net
del plugin
def main_IE_infer():
fps = ""
framepos = 0
frame_count = 0
vidfps = 0
skip_frame = 0
elapsedTime = 0
args = build_argparser().parse_args()
#model_xml = "lrmodels/tiny-YoloV3/FP32/frozen_tiny_yolo_v3.xml" #<--- CPU
model_xml = "/home/saket/openvino_models/tiger/km_adam_yolov3_tinytiger_ckpt_9.xml" #<--- MYRIAD
model_bin = os.path.splitext(model_xml)[0] + ".bin"
'''
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FPS, 30)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, camera_width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, camera_height)
'''
#cap = cv2.VideoCapture("data/input/testvideo.mp4")
#camera_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
#camera_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
#frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
#vidfps = int(cap.get(cv2.CAP_PROP_FPS))
#print("videosFrameCount =", str(frame_count))
#print("videosFPS =", str(vidfps))
time.sleep(1)
plugin = IEPlugin(device=args.device)
if "CPU" in args.device:
plugin.add_cpu_extension("lib/libcpu_extension.so")
net = IENetwork(model=model_xml, weights=model_bin)
input_blob = next(iter(net.inputs))
exec_net = plugin.load(network=net)
import glob
images = glob.glob('/media/saket/014178da-fdf2-462c-b901-d5f4dbce2e275/nn/PyTorch-YOLOv3/data/tigersamples/*.jpg')
print ('Num images',len(images))
counter = 0
while cv2.waitKey(0):
if cv2.waitKey(1)&0xFF == ord('q') or counter>len(images)-1:
break
t1 = time.time()
image = np.asarray(Image.open(images[counter]).convert('RGB'))
master = np.zeros((1920, 1920, 3),dtype='uint8')
master[420:1500,:]=image
image = master
camera_height, camera_width = image.shape[0:2]
new_w,new_h = 416,416
resized_image = cv2.resize(image, (new_w, new_h), interpolation = cv2.INTER_CUBIC)
canvas = np.full((m_input_size, m_input_size, 3), 0)
canvas[(m_input_size-new_h)//2:(m_input_size-new_h)//2 + new_h,(m_input_size-new_w)//2:(m_input_size-new_w)//2 + new_w, :] = resized_image
prepimg = canvas
prepimg = prepimg[np.newaxis, :, :, :] # Batch size axis add
prepimg = prepimg.transpose((0, 3, 1, 2)) # NHWC to NCHW
#print (prepimg.shape)
outputs = exec_net.infer(inputs={input_blob: prepimg})
objects = []
#output_name = detector/yolo-v3-tiny/Conv_12/BiasAdd/YoloRegion
#output_name = detector/yolo-v3-tiny/Conv_9/BiasAdd/YoloRegion
objects = []
for output in outputs.values():
objects = ParseYOLOV3Output(output,new_h, new_w, camera_height, camera_width, 0.5, objects)
# Filtering overlapping boxes
objlen = len(objects)
for i in range(objlen):
if (objects[i].confidence == 0.0):
continue
for j in range(i + 1, objlen):
if (IntersectionOverUnion(objects[i], objects[j]) >= 0.5):
if objects[i].confidence < objects[j].confidence:
objects[i], objects[j] = objects[j], objects[i]
objects[j].confidence = 0.0
# Drawing boxes
image = image[420:1500,:]
print (image.shape)
for obj in objects:
if obj.confidence < 0.5:
continue
label = obj.class_id
confidence = obj.confidence
if confidence > 0.5:
label_text = LABELS[label] + " (" + "{:.1f}".format(confidence * 100) + "%)"
cv2.rectangle(image, (obj.xmin, obj.ymin-420), (obj.xmax, obj.ymax-420), box_color, box_thickness)
cv2.putText(image, label_text, (obj.xmin, obj.ymin - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, label_text_color, 1)
cv2.putText(image, fps, (camera_width - 170, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (38, 0, 255), 1, cv2.LINE_AA)
cv2.imshow("Result", image)
elapsedTime = time.time() - t1
fps = "(Playback) {:.1f} FPS".format(1/elapsedTime)
## frame skip, video file only
#skip_frame = int((vidfps - int(1/elapsedTime)) / int(1/elapsedTime))
#framepos += skip_frame
counter= counter+1
cv2.destroyAllWindows()
del net
del exec_net
del plugin
