caffe 模型转换为rknn后 识别一直错

根据demo的代码转换caffe模型  转换成功了 可是预测结果一直不对
求大佬看下问题
# Create RKNN object
rknn = RKNN()

# pre-process config
print('--> config model')
rknn.config(channel_mean_value='84.29 84.8 83.61 1', reorder_channel='2 1 0')
print('done')

# Load tensorflow model
print('--> Loading model')
ret = rknn.load_caffe(model='./model.prototxt',
                      proto='caffe',
                      blobs='./model.caffemodel')
if ret != 0:
    print('Load mobilenet_v2 failed! Ret = {}'.format(ret))
    exit(ret)
print('done')

# Build model
print('--> Building model')
ret = rknn.build(do_quantization=False)
if ret != 0:
    print('Build mobilenet_v2 failed!')
    exit(ret)
print('done')

# Export rknn model
print('--> Export RKNN model')
ret = rknn.export_rknn('./model.rknn')
if ret != 0:
    print('Export mobilenet_v2.rknn failed!')
    exit(ret)
print('done')

# Set inputs
img = cv2.imread('./000.jpg')
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

print('--> Init runtime environment')
ret = rknn.init_runtime()
if ret != 0:
    print('Init runtime environment failed')
    exit(ret)
print('done')

# Inference
print('--> Running model')
outputs = rknn.inference(inputs=[img])
show_outputs(outputs)
print('done')