ONNX Slice转换报错

--> Loading model
I Start importing onnx...
W Call onnx.optimizer.optimize fail, skip optimize
I Current ONNX Model use ir_version 6 opset_version 11
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_426 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_423 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_420 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_406 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_403 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_400 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_386 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_383 (1,)
W Infer onnx shape: Meet empty shape tensor, reshape () to (1,)!
D Calc tensor Constant_380 (1,)

.....

I Try match Slice_Slice_39ut0
W Not match tensor Slice_Slice_39ut0
E Try match Slice_Slice_39ut0 failed, catch exception!
W ----------------Warning(12)----------------
E Catch exception when loading onnx model: yolov5s.onnx!
E Traceback (most recent call last):
E   File "rknn/base/RKNNlib/converter/convert_onnx.py", line 1152, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx.match_paragraph_and_param
E   File "rknn/base/RKNNlib/converter/convert_onnx.py", line 1054, in rknn.base.RKNNlib.converter.convert_onnx.convert_onnx._onnx_push_ready_tensor

使用Netron查看ONNX 模型， 存在节点 Slice_Slice_39

out = self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
这里 Slice 操作的 Step = 2， 应该是RKNN不支持导致的问题，，， 有谁知道怎么处理吗？

自问自答，解决方案：
使用其他操作替代原来步长为2的切片操作，如下修改测试时可以的：
        pooled = self.maxpool2d(x) #[N, 4*C, W/2, H/2]
        reutrn self.conv( torch.cat([pooled, pooled, pooled, pooled], 1))

You changed the layer's operation like that though. The shape will be the same, but slice and maxpool do different operations, your network will behave wrong after that modification.

rakidis 发表于 2021-9-21 21:22
You changed the layer's operation like that though. The shape will be the same, but slice and maxpoo ...

absolutely agree

rakidis 发表于 2021-9-21 21:22
You changed the layer's operation like that though. The shape will be the same, but slice and maxpoo ...

Thanks for you reply.
That's true. Then I replace maxpool with conv operation and retrain the model. The mAP seems not degrade too much.
Just provide a guide for sb. who might encounter similar issue.

May I ask which neural network you were trying to convert spesifically? I bumped into similiar situation and managed to solve it with another method