This project is mirrored from https://gitcode.net/xiaomi/mace.git.
Pull mirroring failed .
Repository mirroring has been paused due to too many failed attempts. It can be resumed by a project maintainer.
Repository mirroring has been paused due to too many failed attempts. It can be resumed by a project maintainer.
- 23 Oct, 2020 2 commits
- 21 Oct, 2020 3 commits
-
-
李滨 authored
opt: reduce the so size for bazel and fix error in cmake compile See merge request applied-machine-learning/sysml/mace!1307
-
luxuhui authored
N/A Signed-off-by:Luxuhui <luxuhui@xiaomi.com>
-
卢旭辉 authored
fix: Fix folding MatMul BiasAdd See merge request applied-machine-learning/sysml/mace!1306
-
- 20 Oct, 2020 1 commit
-
-
Bin Li authored
-
- 15 Oct, 2020 2 commits
-
-
卢旭辉 authored
Fix micro matmul bias access bug See merge request applied-machine-learning/sysml/mace!1304
-
Zhang Zhimin authored
-
- 14 Oct, 2020 6 commits
-
-
李超 authored
fix: fix `Transpose` op's computing error on batch tensor. See merge request applied-machine-learning/sysml/mace!1302
-
李超 authored
perf: opt `reduce` op's performance on GPU See merge request applied-machine-learning/sysml/mace!1301
-
luxuhui authored
N/A Signed-off-by: -
Riccardo authored
Co-authored-by:gasgallo <rgall@sertiscorp.com>
-
卢旭辉 authored
feat: Add bf16 kernels for MobileNet See merge request applied-machine-learning/sysml/mace!1298
-
luxuhui authored
N/A Signed-off-by:
-
- 27 Sep, 2020 1 commit
-
-
Bin Li authored
-
- 24 Sep, 2020 1 commit
-
-
卢旭辉 authored
perf: Prefer GPU if input ops on different devices See merge request applied-machine-learning/sysml/mace!1297
-
- 23 Sep, 2020 1 commit
-
-
Bin Li authored
-
- 21 Sep, 2020 2 commits
-
-
李超 authored
feat: support FusedBatchNormV2/FusedBatchNormV3 for tensorflow See merge request applied-machine-learning/sysml/mace!1296
-
luxuhui authored
N/A Signed-off-by:
-
- 31 Aug, 2020 3 commits
-
-
卢旭辉 authored
add micro concat op See merge request applied-machine-learning/sysml/mace!1295
-
Zhang Zhimin authored
-
卢旭辉 authored
Add onnx's Elu operator See merge request applied-machine-learning/sysml/mace!1294
-
- 27 Aug, 2020 1 commit
-
-
lichao18 authored
-
- 25 Aug, 2020 1 commit
-
-
卢旭辉 authored
Add quantized Relu/BiasAdd/Pad/Transpose for CPU See merge request applied-machine-learning/sysml/mace!1292
-
- 21 Aug, 2020 1 commit
-
-
李超 authored
fix: set Deconv2d filter's opencl buffer type to CONV2D_FILTER See merge request applied-machine-learning/sysml/mace!1293
-
- 19 Aug, 2020 1 commit
-
-
Bin Li authored
-
- 18 Aug, 2020 1 commit
-
-
luxuhui authored
N/A Signed-off-by:
-
- 03 Aug, 2020 1 commit
-
-
李超 authored
fix: delete `Delay` op's benchmark code See merge request applied-machine-learning/sysml/mace!1287
-
- 30 Jul, 2020 2 commits
- 22 Jul, 2020 1 commit
-
-
Yi-Kai-Chen authored
* Margaux dev. * Support Pad, Activation, Mul operator for mnasnet * Support document enhance model * Apply add-init-cache-and-preemption patch * Refine code * Add APU int16 quantization and fix macro bugs * Refine code Co-authored-by:
YungChien Hsu <yungchien.hsu@mediatek.com> Co-authored-by:
Eric Chen <eric-yk.chen@mediatek.com>
-
- 20 Jul, 2020 3 commits
-
-
卢旭辉 authored
Update APU support See merge request applied-machine-learning/sysml/mace!1283
-
luxuhui authored
N/A Signed-off-by: -
李滨 authored
feat: support extract_image_patches op and support dynamic filter of conv2d/deconv2d See merge request applied-machine-learning/sysml/mace!1286
-
- 17 Jul, 2020 2 commits
-
-
luxuhui authored
N/A Signed-off-by: -
YungChien Hsu authored
Signed-off-by:lichao18 <lichao18@xiaomi.com> Add init cache and preemption Support mnasnet and new 5g library Add GetModelSize API for model header
-
- 16 Jul, 2020 2 commits
- 15 Jul, 2020 1 commit
-
-
Bin Li authored
-
- 10 Jul, 2020 1 commit
-
-
李滨 authored
fix: fix the interface compatibility issue See merge request applied-machine-learning/sysml/mace!1282
-
