def detect(img_path):
#------------------preprocessing------------------------
ori_imgs, framed_imgs, framed_metas = preprocess(
img_path, max_size=input_size) #input_size: 512
x = torch.stack([torch.from_numpy(fi).cuda() for fi in framed_imgs], 0)
x = x.to(torch.float32 if not use_float16 else torch.float16).permute(
0, 3, 1, 2)
with torch.no_grad():
start = timeutil.get_epochtime_ms()
t1 = time.time()
features, regression, classification, anchors = model(x)
regressBoxes = BBoxTransform()
clipBoxes = ClipBoxes()
out = postprocess(x, anchors, regression, classification, regressBoxes,
clipBoxes, threshold, iou_threshold)
out = invert_affine(framed_metas, out)
c1, c2 = display(out, ori_imgs, imshow=True, imwrite=False)
t2 = time.time()
tact_time = (t2 - t1) / 10
print(f'{tact_time} seconds, {1 / tact_time} FPS, @batch_size 1')
print('milisecond is ' + str(t2 - t1))
print("Latency: %fms" % (timeutil.get_epochtime_ms() - start))
return c1, c2
"color": color,
"pad": 0
},
)
plt.axis("off")
plt.gca().xaxis.set_major_locator(NullLocator())
plt.gca().yaxis.set_major_locator(NullLocator())
filename = path.split("/")[-1].split(".")[0]
plt.savefig(f"output/{filename}.jpg",
bbox_inches="tight",
pad_inches=0.0)
plt.close()
return result_x1, result_y1, result_x2, result_y2, result_box_h
detection = top_detect(weigth_PATH='./weights/yolov3_ckpt_99.pth'
) # change your image path and weight path
start = timeutil.get_epochtime_ms()
x1, y1, x2, y2, box_h = detection.detect(IMG_PATH='sample3.jpg', ) # output
# img = cv2.imread('./sample2.jpg')
# img = cv2.rectangle(img, (int(x1[0]), int(y1[0]+box_h[0])), (int(x2[0]), int(y1[0])), (0,0,255), 2)
# cv2.imshow('result', img)
# cv2.waitKey(0)
print("{} {} {} {}".format(x1[0], y1[0] + box_h[0], x2[0], y1[0]))
print("Latency: %fms" % (timeutil.get_epochtime_ms() - start))
from top_detect import top_detect
import timeutil
detection = top_detect(weigth_PATH='./weights/yolov3_ckpt_99.pth'
) # change your image path and weight path
total_time = 0.0
for i in range(1000):
start = timeutil.get_epochtime_ms()
x1, x2, y1, y2, box_h = detection.detect(IMG_PATH='sample/resize_2.jpg',
conf_thres=0.5,
nms_thres=0.5) # output
total_time += timeutil.get_epochtime_ms() - start
# print("Latency: %fms" % (timeutil.get_epochtime_ms() - start))
print('avg time is ' + str(total_time / 1000))