提交 · b0d9a3aa526303c4f276e7ef1044ab2913f40aea · 慢慢CG / Mace

28 10月, 2020 1 次提交
- L
  
  fix: Add framework_type arg in Net so that we can get it from Net besides Op · b0d9a3aa
  由 like15 提交于 10月 27, 2020
  
  b0d9a3aa
23 10月, 2020 2 次提交
- L
  feat: add Elu for Tensorflow and Caffe and fix bug in reverse op and net adapter · dd2cdb01
  由 luxuhui 提交于 10月 21, 2020
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  dd2cdb01
- B
  
  fix: Use 1 element tensor as scalar for Eltwise · b39b5399
  由 Bin Li 提交于 10月 23, 2020
  
  b39b5399
21 9月, 2020 1 次提交
- L
  feat: support FusedBatchNormV2/FusedBatchNormV3 for tensorflow · 44f7d259
  由 luxuhui 提交于 9月 21, 2020
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  44f7d259
17 7月, 2020 1 次提交
- L
  feat: support extract_image_patches op and support dynamic filter of conv2d/deconv2d · 9472dcee
  由 luxuhui 提交于 6月 24, 2020
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  9472dcee
30 6月, 2020 1 次提交
- L
  feat: support splitV op for tensorflow · 041a5d2e
  由 luxuhui 提交于 6月 29, 2020
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  041a5d2e
17 6月, 2020 1 次提交
- L
  feat: support `half_pixel_centers` arg for `resize` type ops · d24a3ddd
  由 luxuhui 提交于 6月 16, 2020
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  d24a3ddd
28 5月, 2020 1 次提交
- L
  support RELU6/ArgMax/ResizeNearestNeighbor op for Caffe, fix bug. · b5dfcf4d
  由 luxuhui 提交于 5月 11, 2020
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  b5dfcf4d
08 5月, 2020 1 次提交
- R
  Add support for AddV2 op in TF (#637) · ab7499a5
  由 Riccardo 提交于 5月 08, 2020
```
Co-authored-by: Nriccardo <rgall@sertiscorp.com>
```
  ab7499a5
19 2月, 2020 1 次提交
- L
  fix bug on reshape op & tar command & merge_duplicate_nodes · 020455ce
  由 luxuhui 提交于 2月 18, 2020
```
issue:593
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  020455ce
11 1月, 2020 1 次提交
- L
  fix 'op not unique' error in converting model from tf · bc1f0a56
  由 luxuhui 提交于 1月 11, 2020
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  bc1f0a56
06 12月, 2019 1 次提交
- L
  support BatchMatMulV2 & Select ops for tensorflow · 04ecb90e
  由 luxuhui 提交于 12月 04, 2019
```
N/A
Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
```
  04ecb90e
02 12月, 2019 1 次提交
- L
  
  add tf.sign op and reorder tf ops in tf_converter · c5f92ebf
  由 liutuo 提交于 12月 02, 2019
  
  c5f92ebf
29 10月, 2019 2 次提交
- L
  Add CMake and ZH docs · 80a017ce
  由 liyin 提交于 9月 27, 2019
```
Revert "Merge branch 'refactor-python-scripts' into 'master'"

This reverts merge request !1200
```
  80a017ce
- B
  
  Fix quantize info · adb538bf
  由 Bin Li 提交于 10月 28, 2019
  
  adb538bf
28 10月, 2019 4 次提交
- 叶
  support tf.tile · 021e1e25
  由叶剑武提交于 10月 18, 2019
```
fix type error

fix type warning

add TileOp to MaceTransposableDataFormatOps and reduce memcpy in TileOp
```
  021e1e25
- 叶
  
  fix pad converter and support padv2 · 107b956a
  由叶剑武提交于 10月 19, 2019
  
  107b956a
- B
  
  Fix multiple models in one yml · 2f949efb
  由 Bin Li 提交于 10月 11, 2019
  
  2f949efb
- L
  fix data type convert in onnx-converter · 467aefb0
  由 liutuo 提交于 9月 26, 2019
```
refactor structure of python scripts
```
  467aefb0
21 8月, 2019 1 次提交
- L
  
  Fix case output type · 7bc38706
  由 liyin 提交于 8月 21, 2019
  
  7bc38706
12 8月, 2019 1 次提交
- L
  
  Refactor model converter & encrypt process · 320b509c
  由 liyin 提交于 8月 09, 2019
  
  320b509c
12 6月, 2019 1 次提交
- L
  
  Fix a converter bug for tensorflow reduce op · 36cd6339
  由 lichao18 提交于 6月 12, 2019
  
  36cd6339
10 6月, 2019 1 次提交
- L
  
  add reduce sum · 3890a7c5
  由 liutuo 提交于 6月 10, 2019
  
  3890a7c5
15 5月, 2019 1 次提交
- 許
  Integrate MediaTek APU Support (#440) · 2d650b67
  由許永健提交于 5月 15, 2019
```
* Integrate APU

* fix code style issue
```
  2d650b67
22 4月, 2019 1 次提交

Refactor: Support auto transformation and net optimization. · 74dcd617

由 liuqi 提交于 4月 17, 2019

1. Auto transformation between data format, data type and memory type.
2. Add device placement optimization strategy.

74dcd617

17 4月, 2019 1 次提交
- L
  
  convert tf Min and Max to reduce_min and reduce_max · 81a276b1
  由 liutuo 提交于 4月 17, 2019
  
  81a276b1
16 4月, 2019 1 次提交
- L
  update onnx converter · afc440b6
  由 liutuo 提交于 4月 16, 2019
```
add support splite with num_splits=1
```
  afc440b6
03 4月, 2019 1 次提交

Support int32 input data type. · 80d1c9dd

由 liuqi 提交于 4月 02, 2019

1. Support int32 input data type.
2. Support GatherV2 op
3. Add transpose to ExpandDim op.

80d1c9dd

21 3月, 2019 1 次提交
- Y
  
  support tf.cumsum and 4-D strided_slice in cpu · a85f052d
  由 yejianwu 提交于 2月 28, 2019
  
  a85f052d
18 3月, 2019 2 次提交
- L
  
  Support scalar input · 8f9ccc88
  由 liyin 提交于 3月 15, 2019
  
  8f9ccc88
- L
  Feature: Add capability information for mace_run · 36703e80
  由 liuqi 提交于 3月 18, 2019
```
1. add capability show information for mace_run
2. remove flatten_atrous_conv of tensorflow transform_graph
```
  36703e80
13 3月, 2019 1 次提交
- L
  Feature: DepthwiseConv2D supports non-const filter tensor. · c282cb3e
  由 liuqi 提交于 3月 13, 2019
```
1. input_data_formats flag in yaml supports OIHW
2. MaceTensor support OIHW data format
```
  c282cb3e
08 3月, 2019 1 次提交
- L
  
  Quantize matmul only, add gather u8 test. · d2c2897a
  由 liyin 提交于 2月 27, 2019
  
  d2c2897a
21 2月, 2019 1 次提交
- W
  
  Added one_hot() operator. · 6ddd532d
  由 Wiktor Adamski 提交于 2月 21, 2019
  
  6ddd532d
15 2月, 2019 2 次提交
- W
  
  Changed code formatting. · 4418e030
  由 Wiktor Adamski 提交于 2月 15, 2019
  
  4418e030
- W
  
  Added REFLECT and SYMMETRIC modes to the pad() operator. · 230f1425
  由 Wiktor Adamski 提交于 2月 15, 2019
  
  230f1425
12 2月, 2019 1 次提交

Added floordiv() operator (#336) · 9d3e2cc5

由 w-adamski 提交于 2月 12, 2019

* Added floordiv() operator

* Restored original indentation

* Update eltwise.cl

Update eltwise.cl according to the recent fix.

9d3e2cc5

11 2月, 2019 1 次提交
- W
  
  Added sqrt() to tensorflow converter (#343) · 1d11cac2
  由 w-adamski 提交于 2月 11, 2019
  
  1d11cac2
30 1月, 2019 1 次提交
- L
  
  Add resize nearest neighbor · 934d3f26
  由 lichao18 提交于 1月 22, 2019
  
  934d3f26
15 1月, 2019 1 次提交
- P
  Support LeakyRelu conversion from tensorflow (#308) · 740d2dc1
  由 Paul Idstein 提交于 1月 15, 2019
```
* Support LeakyRelu conversion from tensorflow

* Code style PEP8
```
  740d2dc1

慢慢CG / Mace 与 Fork 源项目一致

慢慢CG / Mace
与 Fork 源项目一致