Closed sutongkui closed 5 years ago
Did you change the ninput_edges flag to 3000 (the default is 750)? Do that by passing: --ninput_edges 3000
. Also, I assume that your training architecture also used --pool_res 2500 2000 1500 1000
, otherwise it won't work
oh. I forgot to change the default ninput_edges to 3000. you mean that I need to retrain it with the new pooling size?as we know, the real meshes vary from hundreds to hundreds of thousabds, is there a way to handle this with one net,instead of training once for each size. I am trying to use meshcnn as a new method to handle mesh simplification.just like what simplygon does.
The --pool_res
defines hyper-parameters of the network (aka the network architecture). You cannot use a different network architectures for train / test.
You can re-train the network on your data, define new hyper-parameters for your set, and use the same one for train / test.
@sutongkui - closing this issue as I haven't heard from you in a while. If you still need further clarification , let me know.
As described in #46, I run into this error with files normalized to 300 or 600 faces resulting in about 500 or 1000 edges. I have to set the number of input edges to 2000 to overcome the error.
Works for me now, I have used problematic input data before.
I used classification pretrained parameters, the test works well for edges 750, but then I subdivide the mesh to 3000 edges(apply 1 loop, still manifold), and set
--pool_res 2500 2000 1500 1000
, error occurs below, do I have to use the fixed edges(like 750) as input? How to deal with dense meshes, do we need to retrain it?