-
## 🚀 Tensor and nn.Module Pruning
Tensor method and/or `nn` util to sparsify tensors and/or model, according to various pruning techniques in the literature.
## Motivation
State-of-the-art deep …
-
**Is your feature request related to a problem? Please describe.**
For multi-task learning or calibrationless method the k-support norm is a great structured sparsity norm
**Describe the solution …
-
Hey there,
In many of your examples you seem to be using the test data as validation data, wouldn't this create an overfitted model that is unable to generalise?
Example: https://github.com/fchollet…
-
arXiv论文跟踪
-
Date: 3. Oct 2018
_(aka. honeymoon)_
@doktorgibson
- [x] enablement tools #35
- [x] get [`avc-test-model`](https://gitlab.crowdai.org/florianpfisterer/adversarial-net) to work (docs [here](https…
ghost updated
5 years ago
-
Dear Community, thanks to everyone's effort in the past few months. This is a proposal to do a v0.6 release.
This release will be managed by the TVM PMC, with @yzhliu and myself as moderators. In…
-
By default, Sphinx builds are incremental: If you've recently done a clean build of the docs, and then you modified just one of the sources, the next time you build, Sphinx will only build the pages t…
-
我的目的是借用scnn来压缩模型参数，但是在某些环境下（如安卓系统）缺乏sparseblas库；此时只能采用常规的卷积操作；如果我不用sparseblas测试压缩后的模型，会不会影响测试精度？
-
Hi,
I was trying to reproduce the baseline performance of ConvNet (reported in your NIPS paper). But I tried the default setting (`cifar10_full_multistep_solver.prototxt`) as the provided one in th…
bobye updated
7 years ago
-
### Issue summary
Evaluating your uploaded models in general caffe (https://github.com/BVLC/caffe/tree/master/src/caffe) results in following:
> I0503 16:43:44.044796 19898 caffe.cpp:155] Finetuni…