Skip to content

Commit 6b9e76d

Browse files
winnietsangwinnietsang
authored
Create Release 1.6.0 for tf-1.x branch (#676)
1 parent c6784d4 commit 6b9e76d

8 files changed

+408
-201
lines changed

‎ONNX_VERSION_NUMBER

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
1.5.0
1+
1.6.0

‎README.md

Lines changed: 13 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77

88
[Command Line Interface Documentation](https://github.com/onnx/onnx-tensorflow/blob/master/doc/CLI.md)
99

10-
From ONNX to Tensorflow: `onnx-tf convert -t tf -i /path/to/input.onnx -o /path/to/output.pb`
10+
From ONNX to Tensorflow: `onnx-tf convert -i /path/to/input.onnx -o /path/to/output.pb`
1111

1212
### Convert programmatically:
1313

@@ -34,10 +34,13 @@ ONNX-TF requires ONNX (Open Neural Network Exchange) as an external dependency,
3434

3535
The specific ONNX release version that we support in the master branch of ONNX-TF can be found [here](https://github.com/onnx/onnx-tensorflow/blob/master/ONNX_VERSION_NUMBER). This information about ONNX version requirement is automatically encoded in `setup.py`, therefore users needn't worry about ONNX version requirement when installing ONNX-TF.
3636

37-
To install the latest version of ONNX-TF via pip, run `pip install onnx-tf`.
38-
3937
Because users often have their own preferences for which variant of Tensorflow to install (i.e., a GPU version instead of a CPU version), we do not explicitly require tensorflow in the installation script. It is therefore users' responsibility to ensure that the proper variant of Tensorflow is available to ONNX-TF. Moreover, we require Tensorflow version == 1.15.0.
4038

39+
To install the latest version of ONNX-TF v1.6.0
40+
- Run `git clone https://github.com/onnx/onnx-tensorflow.git && cd onnx-tensorflow`.
41+
- Run `git checkout v1.6.0-tf-1.15`.
42+
- Run `pip install -e .`.
43+
4144
## Development:
4245

4346
### Coverage Status:
@@ -48,8 +51,9 @@ Because users often have their own preferences for which variant of Tensorflow t
4851

4952
### Installation:
5053
- Install ONNX master branch from source.
51-
- Install Tensorflow 1.15.0. (For Tensorflow 2.0 support please refer [here](https://github.com/onnx/onnx-tensorflow/blob/master/README.md/).)
52-
- Run `git clone [email protected]:onnx/onnx-tensorflow.git && cd onnx-tensorflow`.
54+
- Install Tensorflow 1.15.0. (For Tensorflow 2.x support please refer [here](https://github.com/onnx/onnx-tensorflow/blob/master/README.md/).)
55+
- Run `git clone https://github.com/onnx/onnx-tensorflow.git && cd onnx-tensorflow`.
56+
- Run `git checkout tf-1.x`.
5357
- Run `pip install -e .`.
5458

5559
### Folder Structure:
@@ -81,8 +85,8 @@ Testing requires significant hardware resources, but nonetheless, we highly reco
8185

8286
PS. Please ensure your code is backward compatible with older version of ONNX. You can easily test it by running the following [docker container](https://hub.docker.com/r/winnietsang/onnx-tensorflow) with your code. If you don't have Docker installed yet, please follow this link to install [Docker](https://docs.docker.com/install/) on your environment.
8387
```
84-
sudo docker pull winnietsang/onnx-tensorflow:onnx1.6.0-tf1.15.0
85-
sudo docker run -it --name=YOUR-CONTAINER-NAME winnietsang/onnx-tensorflow:onnx1.6.0-tf1.15.0 /bin/bash
88+
sudo docker pull winnietsang/onnx-tensorflow:onnx1.7.0-tf1.15
89+
sudo docker run -it --name=YOUR-CONTAINER-NAME winnietsang/onnx-tensorflow:onnx1.7.0-tf1.15 /bin/bash
8690
git clone https://github.com/YOUR-USERNAME/onnx-tensorflow.git
8791
cd onnx-tensorflow
8892
git checkout -b YOUR-BRANCH --track remotes/origin/YOUR-BRANCH
@@ -93,11 +97,5 @@ python3 -m unittest discover test
9397
#### Test Help:
9498
https://docs.python.org/2/library/unittest.html
9599

96-
## Authors:
97-
Arpith Jacob (IBM Research)
98-
99-
Tian Jin (IBM Research)
100-
101-
Gheorghe-Teodor Bercea (IBM Research)
102-
103-
Wenhao Hu (LeapMind)
100+
#### Note:
101+
Branch tf-1.x is for users who cannot upgrade to Tensorflow 2.x yet. This branch will only support up to ONNX OpSet 12 operators. If any user needs to use operators in OpSet 13 or above, please upgrade Tensoflow to 2.x and use the master branch of this repo. By January 1st, 2021 this branch will switch to maintenance mode only, no new development will be added into this branch from then on.

‎VERSION_NUMBER

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
1.5.0
1+
1.6.0

‎Versioning.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,4 +7,4 @@ ONNX-TensorFlow version|ONNX version|TensorFlow version
77
1.2.1|1.1.2 (opset 4)|1.5
88
1.3.0|1.3.0 (opset 8)|1.13.1
99
1.5.0|1.5.0 (opset 10)|1.15.0
10-
1.6.0|1.6.0 (opset 11)|1.15.0
10+
1.6.0|1.6.0 (opset 11)|1.15.0

‎doc/support_status.md

Lines changed: 168 additions & 168 deletions
Large diffs are not rendered by default.

‎doc/support_status_v1_6_0.md

Lines changed: 203 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,203 @@
1+
# ONNX-Tensorflow Support Status
2+
|||
3+
|-:|:-|
4+
|ONNX-Tensorflow Version|v1.6.0|
5+
|ONNX Version|v1.6.0|
6+
|Tensorflow Version|v1.15.0|
7+
8+
Notes:
9+
* Values that are new or updated from a previous opset version are in bold.
10+
* -: not defined in corresponding ONNX opset version
11+
* \*: the operator is deprecated
12+
* :small_red_triangle:: not supported yet
13+
* :small_orange_diamond:: partially supported
14+
* the rest are all supported
15+
16+
||||||||||||||
17+
|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|
18+
|**ONNX Operator**|**Opset 1**|**Opset 2**|**Opset 3**|**Opset 4**|**Opset 5**|**Opset 6**|**Opset 7**|**Opset 8**|**Opset 9**|**Opset 10**|**Opset 11**|**ONNX Operator**|
19+
|Abs|**1**|1|1|1|1|**6**|6|6|6|6|6|Abs|
20+
|Acos|-|-|-|-|-|-|**7**|7|7|7|7|Acos|
21+
|Acosh|-|-|-|-|-|-|-|-|**9**|9|9|Acosh|
22+
|Add|**1**|1|1|1|1|**6**|**7**|7|7|7|7|Add|
23+
|And|**1**|1|1|1|1|1|**7**|7|7|7|7|And|
24+
|ArgMax|**1**|1|1|1|1|1|1|1|1|1|**11**|ArgMax|
25+
|ArgMin|**1**|1|1|1|1|1|1|1|1|1|**11**|ArgMin|
26+
|Asin|-|-|-|-|-|-|**7**|7|7|7|7|Asin|
27+
|Asinh|-|-|-|-|-|-|-|-|**9**|9|9|Asinh|
28+
|Atan|-|-|-|-|-|-|**7**|7|7|7|7|Atan|
29+
|Atanh|-|-|-|-|-|-|-|-|**9**|9|9|Atanh|
30+
|AveragePool|**1**|1|1|1|1|1|**7**|7|7|**10**|**11**|AveragePool|
31+
|BatchNormalization|**1**|1|1|1|1|**6**|**7**|7|**9**|9|9|BatchNormalization|
32+
|BitShift|-|-|-|-|-|-|-|-|-|-|**11**|BitShift|
33+
|Cast|**1**:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|**6**:small_orange_diamond:|6:small_orange_diamond:|6:small_orange_diamond:|**9**:small_orange_diamond:|9:small_orange_diamond:|9:small_orange_diamond:|Cast|
34+
|Ceil|**1**|1|1|1|1|**6**|6|6|6|6|6|Ceil|
35+
|Clip|**1**:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|**6**:small_orange_diamond:|6:small_orange_diamond:|6:small_orange_diamond:|6:small_orange_diamond:|6:small_orange_diamond:|**11**:small_orange_diamond:|Clip|
36+
|Compress|-|-|-|-|-|-|-|-|**9**|9|**11**|Compress|
37+
|Concat|**1**|1|1|**4**|4|4|4|4|4|4|**11**|Concat|
38+
|ConcatFromSequence|-|-|-|-|-|-|-|-|-|-|**11**:small_red_triangle:|ConcatFromSequence|
39+
|Constant|**1**|1|1|1|1|1|1|1|**9**|9|**11**|Constant|
40+
|ConstantOfShape|-|-|-|-|-|-|-|-|**9**|9|9|ConstantOfShape|
41+
|Conv|**1**|1|1|1|1|1|1|1|1|1|**11**|Conv|
42+
|ConvInteger|-|-|-|-|-|-|-|-|-|**10**|10|ConvInteger|
43+
|ConvTranspose|**1**:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|**11**:small_orange_diamond:|ConvTranspose|
44+
|Cos|-|-|-|-|-|-|**7**|7|7|7|7|Cos|
45+
|Cosh|-|-|-|-|-|-|-|-|**9**|9|9|Cosh|
46+
|CumSum|-|-|-|-|-|-|-|-|-|-|**11**:small_orange_diamond:|CumSum|
47+
|DepthToSpace|**1**|1|1|1|1|1|1|1|1|1|**11**|DepthToSpace|
48+
|DequantizeLinear|-|-|-|-|-|-|-|-|-|**10**|10|DequantizeLinear|
49+
|Det|-|-|-|-|-|-|-|-|-|-|**11**|Det|
50+
|Div|**1**|1|1|1|1|**6**|**7**|7|7|7|7|Div|
51+
|Dropout|**1**|1|1|1|1|**6**|**7**|7|7|**10**|10|Dropout|
52+
|DynamicQuantizeLinear|-|-|-|-|-|-|-|-|-|-|**11**|DynamicQuantizeLinear|
53+
|Elu|**1**|1|1|1|1|**6**|6|6|6|6|6|Elu|
54+
|Equal|**1**:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|**7**:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|**11**:small_orange_diamond:|Equal|
55+
|Erf|-|-|-|-|-|-|-|-|**9**|9|9|Erf|
56+
|Exp|**1**|1|1|1|1|**6**|6|6|6|6|6|Exp|
57+
|Expand|-|-|-|-|-|-|-|**8**|8|8|8|Expand|
58+
|EyeLike|-|-|-|-|-|-|-|-|**9**|9|9|EyeLike|
59+
|Flatten|**1**|1|1|1|1|1|1|1|**9**|9|**11**|Flatten|
60+
|Floor|**1**|1|1|1|1|**6**|6|6|6|6|6|Floor|
61+
|GRU|**1**:small_orange_diamond:|1:small_orange_diamond:|**3**:small_orange_diamond:|3:small_orange_diamond:|3:small_orange_diamond:|3:small_orange_diamond:|**7**:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|GRU|
62+
|Gather|**1**|1|1|1|1|1|1|1|1|1|**11**|Gather|
63+
|GatherElements|-|-|-|-|-|-|-|-|-|-|**11**|GatherElements|
64+
|GatherND|-|-|-|-|-|-|-|-|-|-|**11**|GatherND|
65+
|Gemm|**1**|1|1|1|1|**6**|**7**|7|**9**|9|**11**|Gemm|
66+
|GlobalAveragePool|**1**|1|1|1|1|1|1|1|1|1|1|GlobalAveragePool|
67+
|GlobalLpPool|**1**|**2**|2|2|2|2|2|2|2|2|2|GlobalLpPool|
68+
|GlobalMaxPool|**1**|1|1|1|1|1|1|1|1|1|1|GlobalMaxPool|
69+
|Greater|**1**|1|1|1|1|1|**7**|7|**9**|9|9|Greater|
70+
|HardSigmoid|**1**|1|1|1|1|**6**|6|6|6|6|6|HardSigmoid|
71+
|Hardmax|**1**|1|1|1|1|1|1|1|1|1|**11**|Hardmax|
72+
|Identity|**1**|1|1|1|1|1|1|1|1|1|1|Identity|
73+
|If|**1**|1|1|1|1|1|1|1|1|1|**11**|If|
74+
|InstanceNormalization|**1**|1|1|1|1|**6**|6|6|6|6|6|InstanceNormalization|
75+
|IsInf|-|-|-|-|-|-|-|-|-|**10**|10|IsInf|
76+
|IsNaN|-|-|-|-|-|-|-|-|**9**|9|9|IsNaN|
77+
|LRN|**1**|1|1|1|1|1|1|1|1|1|1|LRN|
78+
|LSTM|**1**:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|**7**:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|LSTM|
79+
|LeakyRelu|**1**|1|1|1|1|**6**|6|6|6|6|6|LeakyRelu|
80+
|Less|**1**|1|1|1|1|1|**7**|7|**9**|9|9|Less|
81+
|Log|**1**|1|1|1|1|**6**|6|6|6|6|6|Log|
82+
|LogSoftmax|**1**|1|1|1|1|1|1|1|1|1|**11**|LogSoftmax|
83+
|Loop|**1**|1|1|1|1|1|1|1|1|1|**11**|Loop|
84+
|LpNormalization|**1**|1|1|1|1|1|1|1|1|1|1|LpNormalization|
85+
|LpPool|**1**|**2**|2|2|2|2|2|2|2|2|**11**|LpPool|
86+
|MatMul|**1**|1|1|1|1|1|1|1|**9**|9|9|MatMul|
87+
|MatMulInteger|-|-|-|-|-|-|-|-|-|**10**|10|MatMulInteger|
88+
|Max|**1**|1|1|1|1|**6**|6|**8**|8|8|8|Max|
89+
|MaxPool|**1**:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|**8**:small_orange_diamond:|8:small_orange_diamond:|**10**:small_orange_diamond:|**11**:small_orange_diamond:|MaxPool|
90+
|MaxRoiPool|**1**:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|MaxRoiPool|
91+
|MaxUnpool|-|-|-|-|-|-|-|-|**9**|9|**11**|MaxUnpool|
92+
|Mean|**1**|1|1|1|1|**6**|6|**8**|8|8|8|Mean|
93+
|MeanVarianceNormalization|-|-|-|-|-|-|-|-|**9**|9|9|MeanVarianceNormalization|
94+
|Min|**1**|1|1|1|1|**6**|6|**8**|8|8|8|Min|
95+
|Mod|-|-|-|-|-|-|-|-|-|**10**:small_orange_diamond:|10:small_orange_diamond:|Mod|
96+
|Mul|**1**|1|1|1|1|**6**|**7**|7|7|7|7|Mul|
97+
|Multinomial|-|-|-|-|-|-|**7**:small_red_triangle:|7:small_red_triangle:|7:small_red_triangle:|7:small_red_triangle:|7:small_red_triangle:|Multinomial|
98+
|Neg|**1**|1|1|1|1|**6**|6|6|6|6|6|Neg|
99+
|NonMaxSuppression|-|-|-|-|-|-|-|-|-|**10**|**11**|NonMaxSuppression|
100+
|NonZero|-|-|-|-|-|-|-|-|**9**|9|9|NonZero|
101+
|Not|**1**|1|1|1|1|1|1|1|1|1|1|Not|
102+
|OneHot|-|-|-|-|-|-|-|-|**9**:small_orange_diamond:|9:small_orange_diamond:|**11**:small_orange_diamond:|OneHot|
103+
|Or|**1**|1|1|1|1|1|**7**|7|7|7|7|Or|
104+
|PRelu|**1**|1|1|1|1|**6**|**7**|7|**9**|9|9|PRelu|
105+
|Pad|**1**|**2**|2|2|2|2|2|2|2|2|**11**|Pad|
106+
|Pow|**1**|1|1|1|1|1|**7**|7|7|7|7|Pow|
107+
|QLinearConv|-|-|-|-|-|-|-|-|-|**10**|10|QLinearConv|
108+
|QLinearMatMul|-|-|-|-|-|-|-|-|-|**10**|10|QLinearMatMul|
109+
|QuantizeLinear|-|-|-|-|-|-|-|-|-|**10**|10|QuantizeLinear|
110+
|RNN|**1**:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|1:small_orange_diamond:|**7**:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|7:small_orange_diamond:|RNN|
111+
|RandomNormal|**1**|1|1|1|1|1|1|1|1|1|1|RandomNormal|
112+
|RandomNormalLike|**1**|1|1|1|1|1|1|1|1|1|1|RandomNormalLike|
113+
|RandomUniform|**1**|1|1|1|1|1|1|1|1|1|1|RandomUniform|
114+
|RandomUniformLike|**1**|1|1|1|1|1|1|1|1|1|1|RandomUniformLike|
115+
|Range|-|-|-|-|-|-|-|-|-|-|**11**|Range|
116+
|Reciprocal|**1**|1|1|1|1|**6**|6|6|6|6|6|Reciprocal|
117+
|ReduceL1|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceL1|
118+
|ReduceL2|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceL2|
119+
|ReduceLogSum|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceLogSum|
120+
|ReduceLogSumExp|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceLogSumExp|
121+
|ReduceMax|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceMax|
122+
|ReduceMean|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceMean|
123+
|ReduceMin|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceMin|
124+
|ReduceProd|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceProd|
125+
|ReduceSum|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceSum|
126+
|ReduceSumSquare|**1**|1|1|1|1|1|1|1|1|1|**11**|ReduceSumSquare|
127+
|Relu|**1**|1|1|1|1|**6**|6|6|6|6|6|Relu|
128+
|Reshape|**1**|1|1|1|**5**|5|5|5|5|5|5|Reshape|
129+
|Resize|-|-|-|-|-|-|-|-|-|**10**:small_orange_diamond:|**11**:small_orange_diamond:|Resize|
130+
|ReverseSequence|-|-|-|-|-|-|-|-|-|**10**|10|ReverseSequence|
131+
|RoiAlign|-|-|-|-|-|-|-|-|-|**10**:small_red_triangle:|10:small_red_triangle:|RoiAlign|
132+
|Round|-|-|-|-|-|-|-|-|-|-|**11**|Round|
133+
|Scan|-|-|-|-|-|-|-|**8**|**9**|9|**11**|Scan|
134+
|Scatter|-|-|-|-|-|-|-|-|**9**|9|**11**\*|Scatter|
135+
|ScatterElements|-|-|-|-|-|-|-|-|-|-|**11**|ScatterElements|
136+
|ScatterND|-|-|-|-|-|-|-|-|-|-|**11**|ScatterND|
137+
|Selu|**1**|1|1|1|1|**6**|6|6|6|6|6|Selu|
138+
|SequenceAt|-|-|-|-|-|-|-|-|-|-|**11**|SequenceAt|
139+
|SequenceConstruct|-|-|-|-|-|-|-|-|-|-|**11**|SequenceConstruct|
140+
|SequenceEmpty|-|-|-|-|-|-|-|-|-|-|**11**|SequenceEmpty|
141+
|SequenceErase|-|-|-|-|-|-|-|-|-|-|**11**|SequenceErase|
142+
|SequenceInsert|-|-|-|-|-|-|-|-|-|-|**11**|SequenceInsert|
143+
|SequenceLength|-|-|-|-|-|-|-|-|-|-|**11**|SequenceLength|
144+
|Shape|**1**|1|1|1|1|1|1|1|1|1|1|Shape|
145+
|Shrink|-|-|-|-|-|-|-|-|**9**|9|9|Shrink|
146+
|Sigmoid|**1**|1|1|1|1|**6**|6|6|6|6|6|Sigmoid|
147+
|Sign|-|-|-|-|-|-|-|-|**9**|9|9|Sign|
148+
|Sin|-|-|-|-|-|-|**7**|7|7|7|7|Sin|
149+
|Sinh|-|-|-|-|-|-|-|-|**9**|9|9|Sinh|
150+
|Size|**1**|1|1|1|1|1|1|1|1|1|1|Size|
151+
|Slice|**1**|1|1|1|1|1|1|1|1|**10**|**11**|Slice|
152+
|Softmax|**1**|1|1|1|1|1|1|1|1|1|**11**|Softmax|
153+
|Softplus|**1**|1|1|1|1|1|1|1|1|1|1|Softplus|
154+
|Softsign|**1**|1|1|1|1|1|1|1|1|1|1|Softsign|
155+
|SpaceToDepth|**1**|1|1|1|1|1|1|1|1|1|1|SpaceToDepth|
156+
|Split|**1**|**2**|2|2|2|2|2|2|2|2|**11**|Split|
157+
|SplitToSequence|-|-|-|-|-|-|-|-|-|-|**11**:small_red_triangle:|SplitToSequence|
158+
|Sqrt|**1**|1|1|1|1|**6**|6|6|6|6|6|Sqrt|
159+
|Squeeze|**1**|1|1|1|1|1|1|1|1|1|**11**|Squeeze|
160+
|StringNormalizer|-|-|-|-|-|-|-|-|-|**10**:small_red_triangle:|10:small_red_triangle:|StringNormalizer|
161+
|Sub|**1**|1|1|1|1|**6**|**7**|7|7|7|7|Sub|
162+
|Sum|**1**|1|1|1|1|**6**|6|**8**|8|8|8|Sum|
163+
|Tan|-|-|-|-|-|-|**7**|7|7|7|7|Tan|
164+
|Tanh|**1**|1|1|1|1|**6**|6|6|6|6|6|Tanh|
165+
|TfIdfVectorizer|-|-|-|-|-|-|-|-|**9**|9|9|TfIdfVectorizer|
166+
|ThresholdedRelu|-|-|-|-|-|-|-|-|-|**10**|10|ThresholdedRelu|
167+
|Tile|**1**|1|1|1|1|**6**|6|6|6|6|6|Tile|
168+
|TopK|**1**|1|1|1|1|1|1|1|1|**10**|**11**|TopK|
169+
|Transpose|**1**|1|1|1|1|1|1|1|1|1|1|Transpose|
170+
|Unique|-|-|-|-|-|-|-|-|-|-|**11**:small_red_triangle:|Unique|
171+
|Unsqueeze|**1**|1|1|1|1|1|1|1|1|1|**11**|Unsqueeze|
172+
|Upsample|**1**:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|1:small_red_triangle:|**7**:small_orange_diamond:|7:small_orange_diamond:|**9**:small_orange_diamond:|**10**\*|10\*|Upsample|
173+
|Where|-|-|-|-|-|-|-|-|**9**|9|9|Where|
174+
|Xor|**1**|1|1|1|1|1|**7**|7|7|7|7|Xor|
175+
176+
ONNX-TF Supported Operators / ONNX Operators: 149 / 156
177+
178+
Notes:
179+
1. Cast: Cast string to float32/float64/int32/int64 are not supported in Tensorflow.
180+
2. Clip: Clip input in uint64 is not supported in Tensorflow.
181+
3. ConvTranspose: ConvTranspose with dilations != 1, or transposed convolution for 4D or higher are not supported in Tensorflow.
182+
4. CumSum: CumSum inputs in uint32/uint64 are not supported in Tensorflow.
183+
5. Equal: Equal inputs in uint16/uint32/uint64 are not supported in Tensorflow.
184+
6. GRU: GRU with clip or GRU with linear_before_reset, or GRU not using sigmoid for z and r, or GRU using Elu as the activation function with alpha != 1, or GRU using HardSigmoid as the activation function with alpha != 0.2 or beta != 0.5 are not supported in TensorFlow.
185+
7. LSTM: LSTM not using sigmoid for `f`, or LSTM not using the same activation for `g` and `h` are not supported in Tensorflow.
186+
8. MaxPool: MaxPoolWithArgmax with pad is None or incompatible mode, or MaxPoolWithArgmax with 4D or higher input, orMaxPoolWithArgmax with column major are not supported in Tensorflow.
187+
9. Mod: Mod Dividend or Divisor in int8/int16/uint8/uint16/uint32/uint64 are not supported in Tensorflow.
188+
10. OneHot: OneHot indices in uint16/uint32/uint64/int8/int16/float16/float/double, or OneHot depth in uint8/uint16/uint32/uint64/int8/int16/int64/float16/float/double are not supported in Tensorflow.
189+
11. RNN: RNN with clip is not supported in Tensorflow.
190+
12. Resize: Resize required 4D input in Tensorflow. For opset 11, only the following attributes and inputs conbination are supported in Tensorflow:
191+
1. mode=nearest, coordinate_transformation_mode=align_corners, nearest_mode=round_prefer_ceil, can use scales(*) or sizes.
192+
2. mode=nearest, coordinate_transformation_mode=asymmetric, nearest_mode=floor, can use scales(*) or sizes.
193+
3. mode=nearest, coordinate_transformation_mode=tf_half_pixel_for_nn, nearest_mode=floor, can use scales(*) or sizes.
194+
4. mode=linear, coordinate_transformation_mode=align_corners, can use scales(*) or sizes.
195+
5. mode=linear, coordinate_transformation_mode=asymmetric, can use scales(*) or sizes.
196+
6. mode=linear, coordinate_transformation_mode=half_pixel, can use scales(*) or sizes.
197+
7. mode=cubic, coordinate_transformation_mode=align_corners, cubic_coeff_a=-0.5, exclude_outside=1, can use scales(*) or sizes.
198+
8. mode=cubic, coordinate_transformation_mode=asymmetric, cubic_coeff_a=-0.5, exclude_outside=1, can use scales(*) or sizes.
199+
9. mode=cubic, coordinate_transformation_mode=half_pixel, cubic_coeff_a=-0.5, exclude_outside=1, can use scales(*) or sizes.
200+
10. mode=nearest, coordinate_transformation_mode=tf_crop_and_resize, extrapolation_value=any_float_value, nearest_mode=round_prefer_ceil, can use scales or sizes.
201+
11. mode=linear, coordinate_transformation_mode=tf_crop_and_resize, extrapolation_value=any_float_value, can use scales or sizes.
202+
- Note (*): The accuracy of your model will go down, if the height and the width of the new sizes(scales * origial sizes) are not in whole numbers.
203+
13. Upsample: Upsample required 4D input in Tensorflow.

0 commit comments

Comments
 (0)