我是 openCV - CUDA 的新手，所以我一直在测试最简单的一个，它在 GPU 而不是 CPU 上加载模型，以查看 GPU 的速度有多快，我对得到的结果感到震惊。
----------------------------------------------------------------
--- GPU vs CPU ---
--- ---
--- 21.913758993148804 seconds ---3.0586464405059814 seconds ---
--- 22.379303455352783 seconds ---3.1384341716766357 seconds ---
--- 21.500431060791016 seconds ---2.9400241374969482 seconds ---
--- 21.292986392974854 seconds ---3.3738017082214355 seconds ---
--- 20.88358211517334 seconds ---3.388749599456787 seconds ---
我会给出我的代码片段，以防我做错了导致 GPU 时间飙升的问题。
def loadYolo():
net = cv2.dnn.readNet("yolov4.weights", "yolov4.cfg")
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA_FP16)
classes = []
with open("coco.names", "r") as f:
classes = [line.strip() for line in f.readlines()]
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
return net,classes,layer_names,output_layers
@socketio.on('image')
def image(data_image):
sbuf = StringIO()
sbuf.write(data_image)
b = io.BytesIO(base64.b64decode(data_image))
if(str(data_image) == 'data:,'):
pass
else:
pimg = Image.open(b)
frame = cv2.cvtColor(np.array(pimg), cv2.COLOR_RGB2BGR)
frame = resize(frame, width=700)
frame = cv2.flip(frame, 1)
net,classes,layer_names,output_layers=loadYolo()
height, width, channels = frame.shape
blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416),
swapRB=True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
print("--- %s seconds ---" % (time.time() - start_time))
class_ids = []
confidences = []
boxes = []
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.5:
# Object detected
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# Rectangle coordinates
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
font = cv2.FONT_HERSHEY_PLAIN
colors = np.random.uniform(0, 255, size=(len(classes), 3))
for i in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
label = str(classes[class_ids[i]])
color = colors[class_ids[i]]
cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
cv2.putText(frame, label, (x, y + 30), font, 1, color, 2)
imgencode = cv2.imencode('.jpg', frame)[1]
stringData = base64.b64encode(imgencode).decode('utf-8')
b64_src = 'data:image/jpg;base64,'
stringData = b64_src + stringData
emit('response_back', stringData)
我的 Gpu 是 Nvidia 1050 Ti，我的 CPU 是 i5 gen 9，以防有人需要规格。有人可以启发我，因为我现在非常困惑吗？非常感谢
编辑 1：我尝试使用 cv2.dnn.DNN_TARGET_CUDA 而不是 cv2.dnn.DNN_TARGET_CUDA_FP16，但与 CPU 相比，时间仍然很糟糕。以下是 GPU 结果：
--- 10.91195559501648 seconds ---
--- 11.344025135040283 seconds ---
--- 11.754926204681396 seconds ---
--- 12.779674530029297 seconds ---
以下是 CPU 结果：
--- 4.780993223190308 seconds ---
--- 4.910650253295898 seconds ---
--- 4.990436553955078 seconds ---
--- 5.246175050735474 seconds ---
它仍然比 CPU 慢
编辑 2： OpenCv 是 4.5.0、CUDA 11.1 和 CUDNN 8.0.1