|
错误信息:
-->loading model
loading model done
--> Init runtime environment
W Flag eval_mem has been set, it will affect the performance of inference!
done
W RKNNAPI: IOCTL_CMD_MEMORY_DETAIL fail, ack=0, data_len=0! Please confirm that it is called after rknn_outputs_get!
E Get memory detail success, but detail is empty!
T NoneType
None
测试代码:
def load_model():
rknn = RKNN()
print('-->loading model')
#rknn.load_rknn('./yolov3_tiny.rknn')
rknn.load_rknn('./rknn_models/car_people_u8_pre.rknn')
print('loading model done')
print('--> Init runtime environment')
ret = rknn.init_runtime(target = 'rk1808', device_id = 'TS018082190800200', eval_mem=True)
if ret != 0:
print('Init runtime environment failed')
exit(ret)
print('done')
return rknn
if __name__ == '__main__':
rknn = load_model()
im_file = './dog.jpg'
im = Image.open(im_file)
im = im.resize((416, 416))
mat = np.asarray(im.convert('RGB'))
out_boxes, out_boxes2, out_boxes3 = rknn.inference(inputs=[mat])
memory_detail = rknn.eval_memory(is_print=True)
print(memory_detail)
请问这是哪里出了问题,没有内存使用的信息
|
|