|
本帖最后由 ldol31627 于 2019-11-1 08:27 编辑
--> Loading model
done
--> Building model
done
--> Exporting model
done
--> Init runtime environment
done
--> Running model
E [op_optimize:161]Create weight bias fail.
E [RK_nn_OpOptimize:185]Optimize node CONV_RELU fail
E [optimize_node_forward:189]Forward optimize node[14] CONV_RELU fail
E Catch exception when init model!
T Traceback (most recent call last):
T File "rknn/api/rknn_base.py", line 625, in rknn.api.rknn_base.RKNNBase.inference
T File "rknn/api/rknn_runtime.py", line 275, in rknn.api.rknn_runtime.RKNNRuntime.build_graph
T Exception: RKNN init failed. error code: RKNN_ERR_FAIL
tf.nn.conv2d(x, w, strides=[1, 2, 2, 1], padding=padding) 不报错
tf.nn.conv2d(x, w, strides=[1, 1, 2, 1], padding=padding) 报错
请问这是什么原因?
|
本帖子中包含更多资源
您需要 登录 才可以下载或查看,没有帐号?立即注册
x
|