-
安卓调用的时候库的时候出现如下错误：
```
I/MACE: mace.cc:127 Creating MaceEngine, MACE version: unknown-20180630
I/MACE: mace.cc:135 Initializing MaceEngine
A/MACE: eltwise.h:815 Check failed: (input0->dim_size() =…
-
There seem to be a lot of ABI differences between 1.8 and 1.8.1 as well as between 1.8.1 and 1.8.3. Are they harmless?
These are the differences between 1.8 and 1.8.1:
```diff
--- libxsmm-1.8-4…
-
Before you open an issue, please make sure you have tried the following steps:
1. Make sure your **environment** is the same with (https://mace.readthedocs.io/en/latest/installation/env_requirement…
-
## 🐛 Bug
Torch fails to build (even with `BUILD_TEST=0`) on `/opt/pytorch/torch/csrc/Dtype.cpp`; looks like another instance of warning converted to errors:
```bash
[0mFirst, rewinding head to…
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**:Ubuntu 18.04
- **NDK version(e.g., 15c)**: r16b
- **GCC version(if compiling for host, e.g., 5.4.0)**: 7.3.0
…
-
Could you please explain what is the rational behind choosing the current tile size for 2D Convolutions for Winograd F(6x6, 3x3).
In the original publication on Winograd transformation, the tile size…
ghost updated
6 years ago
-
Once it's stabilized, currently at https://github.com/gcp/leela-zero/tree/winograd
-
Username:
Linux chandu 4.15.0-24-generic #26~16.04.1-Ubuntu SMP Fri Jun 15 14:35:08 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
This is the process I have followed:
[https://caffe2.ai/docs/getting-st…
-
I try to compare performance of NNPACK with caffe using openblas.I downloaded the latest version of NNAPCK from github and compiled NNPACK as the build guide.For caffe and openblas,I use the latest re…
-
Based on some recent benchmarks (on GTX 1080 Ti), using 8-bit quantized integers during inference could give us significant performance improvement. No experiments has been performed yet, but other so…