ONNX (reference) in projects: dports - OpenGrok search results

Project(s)

Full Search
Definition
Symbol
File Path
History
Type

Searched refs:ONNX (Results 1 – 25 of 300) sorted by relevance

12 3 4 5 6 7 8 9 10 >>...12

/dports/misc/mmdnn/MMdnn-0.3.1/mmdnn/conversion/onnx/
H A D	DEVELOPMENT.md	1 # Some guidance and tips on developing ONNX emitter 3 ## Why do we need ONNX master branch 5 ONNX [versioned each operator it supported](https://github.com/onnx/onnx/blob/master/docs/Operators… 6 …ONNX operator API changed a lot in the latest version 6, and is more compatible with the IR MMdnn … 9 That's why we need the ONNX master branch. 11 ## Why do we need ONNX-TensorFlow 13 ONNX is defined as "a open format to represent deep learning models", for the ease of developing ON… 14 …ONNX backend implementation that we are able to use: the Caffe2 backend ([ONNX-Caffe2](https://git… 16 …that ONNX-TensorFlow supports more ONNX operators than ONNX-Caffe2 especially for version 6, so we… 64 It brings some difficulty while developing ONNX emitter since channel converting is needed. [all …]
H A D	README.md	1 # ONNX README 5 Currently we only implemented the IR -> ONNX part. 7 We'll take Keras DenseNet121 -> ONNX as an example. 13 TensorFlow runs as the backend of both Keras and ONNX. 29 #### Install ONNX frontend and backend 31 Here we use [ONNX-TensorFlow](https://github.com/onnx/onnx-tensorflow) to install ONNX and its Tens… 39 As the IR -> ONNX part is not included in the lastest version of MMdnn, we need to install MMdnn ma… 85 ### Convert DenseNet121 model from Keras to ONNX 101 ONNX model file is saved as [densenet121.onnx], generated by [77a4c18fc6254078ba4daca924eac3ab.py] … 106 ### Load and run ONNX DenseNet121 model [all …]
/dports/misc/py-onnx-tf/onnx-tf-1.6.0/
H A D	README.md	1 # Tensorflow Backend for ONNX 4 ## To convert models from ONNX to Tensorflow: 10 From ONNX to Tensorflow: `onnx-tf convert -i /path/to/input.onnx -o /path/to/output.pb` 14 [From ONNX to Tensorflow](https://github.com/onnx/onnx-tensorflow/blob/master/example/onnx_to_tf.py) 17 We have joined force with Microsoft to co-develop ONNX Tensorflow frontend. 20 ## ONNX model inference with Tensorflow backend: 33 ONNX-TF requires ONNX (Open Neural Network Exchange) as an external dependency, for any issues rela… 35 …ONNX release version that we support in the master branch of ONNX-TF can be found [here](https://g… 37 To install the latest version of ONNX-TF via pip, run `pip install onnx-tf`. 44 [ONNX-Tensorflow Op Coverage Status](https://github.com/onnx/onnx-tensorflow/blob/master/doc/suppor… [all …]
/dports/misc/glow/glow-f24d960e3cc80db95ac0bc17b1900dbf60ca044a/thirdparty/onnx/docs/
H A D	Versioning.md	1 # ONNX versioning 3 This document describes the rules for versioning ONNX. Like the rest of the ONNX 8 ONNX defines the versioning policy and mechanism for three classes of entities: 11 * Operator specifications that may be referenced by a given ONNX graph. We refer to this as the *op… 14 …d largely independent. That is, the ONNX IR format evolves at a different rate than the set operat… 18 …ONNX entities, progressive ONNX _releases_ are assigned increasing version numbers. The release ve… 34 1. A producer of a given ONNX model (and the ONNX specification itself) MUST strictly adhere to the… 35 …ONNX model SHOULD consume an updated ONNX file, provided there are no breaking changes in the new … 36 …A consumer of a given ONNX model MAY consume an updated ONNX file, provided there are one or more … 87 > In practice, this means that BC-breaking changes in the ONNX [all …]
H A D	ImplementingAnOnnxBackend.md	1 ### Implementing an ONNX backend 3 #### What is an ONNX backend 5 …ONNX backend is a library that can run ONNX models. Since many deep learning frameworks already ex… 9 ONNX has defined a unified (Python) backend interface at https://github.com/onnx/onnx/blob/master/o… 15 - `Backend` is the entity that will take an ONNX model with inputs, perform a computation, and then… 23 Note that even though the ONNX unified backend interface is defined in Python, your backend does no… 25 #### ONNX backend test 27 ONNX provides a standard backend test suite to assist backend implementation verification. It's str… 29 Integrating the ONNX Backend Test suite into your CI is simple. The following are some examples dem… 37 …rg/en/latest/) installed, you can get a coverage report after running the ONNX backend test to see… [all …]
H A D	TypeAnnotations.md	1 # Type annotations for ONNX 3 …line with this, we just added type annotations to our python code to help ONNX developers more eas… 5 These type annotations are used by [mypy](https://github.com/python/mypy) within the ONNX CI system… 6 We also have type annotations for our APIs, which means your tools built on top of the ONNX APIs ca… 8 …pect this to have a positive impact on the reliability of ONNX and dependent projects like ONNX co… 14 …ONNX, which converts between ONNX models and the models of some machine learning framework. If you… 16 ## For ONNX contributors 17 If you're contributing to the ONNX repository, you need to add type annotations to your project or …
H A D	CONTRIBUTING.md	3 You will need to install protobuf and numpy to build ONNX. An easy 11 During development, it's convenient to install ONNX in development mode (to disable ONNX-ML, set en… 26 - `checker.py`: a utility to check whether a serialized ONNX proto is legal 28 - `defs/`: a subfolder that defines the ONNX operators 41 ONNX is an open standard, and we encourage developers to contribute high 42 quality operators to ONNX specification. 47 ONNX uses [pytest](https://docs.pytest.org) as a test driver. To run tests, you'll first need to in… 86 * [How to implement ONNX backend (ONNX to something converter)](ImplementingAnOnnxBackend.md) 95 [ONNX Open Source Code of Conduct](http://onnx.ai/codeofconduct.html)
H A D	OnnxBackendTest.md	`1 ### ONNX Backend Test 3 #### What is ONNX Backend Test 5 ONNX Backend Test is a test suite that each ONNX backend should run to verify whether it fulfills O… 10 …re similar to those of Node Tests', but instead of a node, the backend will be given an ONNX model. 14 As ONNX aims to become the spec of deep learning models format, it's important to ensure that there… 18 …rk from admins (like uploading the files to the cloud), so if you have an ONNX model that you woul…`
H A D	VersionConverter.md	`1 # ONNX Version Converter 3 ONNX provides a library for converting ONNX models between different 4 opset versions. The primary motivation is to improve backwards compatibility of ONNX 5 models without having to strengthen the spec for ONNX backends. This 8 …tructs, and converters to and from the protobuf format which were developed for the ONNX Optimizer. 49 to the core ONNX repository`
H A D	ONNXIFI.md	1 # ONNX Interface for Framework Integration (ONNXIFI) 3 ONNXIFI is a cross-platform API for loading and executing ONNX graphs on optimized backends. High-l… 10 - ONNX format for passing model graphs 14 - Dynamic discovery of supported ONNX Operators on each backend 21 ## How to Use ONNX Interface for Framework Integration 23 0. (Optional) Use `onnxifi_load` to dynamically load the ONNX Interface for Framework Integration l… 37 ## How to Implement ONNX Interface for Framework Integration 41 - Support ONNX 1.0 model format. 47 Vendor-provided libraries should adhere to some rules to ensure discovery by ONNX-supported framewo… 61 Hardware vendors are welcome to add their own extensions to ONNX backend interface. The backend int…
H A D	Broadcasting.md	`1 # Broadcasting in ONNX 3 In ONNX, element-wise operators can take inputs with different shape, 5 ONNX supports two types of broadcasting: multidirectional broadcasting and 12 In ONNX, a set of tensors are multidirectional broadcastable to the same shape 30 Multidirectional broadcasting is supported by the following operators in ONNX: 49 In ONNX, tensor B is unidirectional broadcastable to tensor A 67 Unidirectional broadcasting is supported by the following operators in ONNX:`
H A D	Optimizer.md	`1 # ONNX Optimizer 3 ONNX provides a C++ library for performing arbitrary optimizations on 4 ONNX models, as well as a growing list of prepackaged optimization 9 The primary motivation is to share work between the many ONNX backend 11 implemented on ONNX graphs - some will need additional 13 all such passes along with ONNX so that they can be re-used with a 48 …iven a pattern matching constraint. Furthermore every pass written within ONNX must formally give … 73 to the core ONNX repository.`
H A D	Overview.md	`11 …any stage of development or deployment. The Open Neural Network Exchange (ONNX) format is a common… 13 By providing a common representation of the computation graph, ONNX helps developers choose the rig… 15 ONNX is designed to be an open format. We welcome contributions from the community and encourage ev… 20 …e base definition of ONNX includes the necessary support for machine learning algorithms based on …`
/dports/misc/glow/glow-f24d960e3cc80db95ac0bc17b1900dbf60ca044a/thirdparty/onnx/
H A D	README.md	14 # Use ONNX 16 * [Tutorials for creating ONNX models from](https://github.com/onnx/tutorials). 18 # Learn about the ONNX spec 20 * [ONNX intermediate representation spec](docs/IR.md) 25 # Programming utilities for working with ONNX Graphs 32 …thub.com/onnx/onnx/wiki/%5BAnnouncement%5D-ONNX-working-groups-established) and help shape the fut… 37 If you think some operator should be added to ONNX specification, please read 64 You will need an install of protobuf and numpy to build ONNX. One easy 73 You can then install ONNX from PyPi (Note: Set environment variable `ONNX_ML=1` for onnx-ml): 79 You can also build and install ONNX locally from source code: [all …]
/dports/misc/mxnet/incubator-mxnet-1.9.0/docs/python_docs/python/tutorials/packages/onnx/
H A D	index.rst	`18 ONNX chapter 24 :title: Fine-tuning an ONNX model with MXNet/Gluon 30 :title: Running inference on MXNet/Gluon from an ONNX model 33 A tutorial on running inference from an ONNX model. 36 :title: Importing an ONNX model into MXNet 39 How to load a pre-trained ONNX model file into MXNet. 42 :title: Export ONNX Models 45 How to export an MXNet model to the ONNX model format. 53 Export ONNX Models <https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html>`
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/docs/python_docs/python/tutorials/packages/onnx/
H A D	index.rst	`18 ONNX chapter 24 :title: Fine-tuning an ONNX model with MXNet/Gluon 30 :title: Running inference on MXNet/Gluon from an ONNX model 33 A tutorial on running inference from an ONNX model. 36 :title: Importing an ONNX model into MXNet 39 How to load a pre-trained ONNX model file into MXNet. 42 :title: Export ONNX Models 45 How to export an MXNet model to the ONNX model format. 53 Export ONNX Models <https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html>`
/dports/misc/glow/glow-f24d960e3cc80db95ac0bc17b1900dbf60ca044a/docs/
H A D	Serialization.md	7 Glow can load Caffe2 and ONNX protobufs, as well as TorchScript exported from a 8 PyTorch model. For ONNX protobufs, Glow supports loading ops specified by the 9 [ONNX spec](https://github.com/onnx/onnx/blob/master/docs/Operators.md), as well 14 Glow supports exporting ONNX protobufs. One way this is done is by trying to 15 abide by the ONNX spec for ops which can be represented in ONNX. However this 16 can be problematic as not all ops may fit into ONNX. Additionally, if the 18 downside in moving to ONNX and back, as some information may be lost in the 19 conversion from Glow -> ONNX -> Glow. 21 As an alternative, Glow also supports exporting to custom ONNX ops, which are 26 ### Format of custom Glow ops in ONNX [all …]
H A D	ModelLoader.md	`9 …e Glow supports loading ONNX format model directly, we can export models of PyTorch into the ONNX … 39 We provide an util function to export ONNX model from PyTorch pretrained model. Please refer to [ex… 58 After we get the ONNX model, we can load it and run it in Glow.`
/dports/misc/glow/glow-f24d960e3cc80db95ac0bc17b1900dbf60ca044a/thirdparty/onnx/community/
H A D	readme.md	1 # ONNX Open Governance 13 The ONNX community adheres to the following principles: 15 * __Open__: ONNX is open source. See repository guidelines and CLA, below. 30 * Creator of content, promoting and advocating the ONNX specification 65 * Manage the ONNX brand and any outbound marketing. 91 …ONNX format, the build and CI/CD systems for ONNX repositories, publishing release packages for ON… 111 * Report activity in overall ONNX community meetings 148 All repositories under the ONNX github org: 150 * Must adopt the ONNX Code of Conduct 152 * Must adopt the ONNX CLA bot [all …]
H A D	working-groups.md	3 As described in the ONNX [governance](https://github.com/onnx/onnx/tree/master/community#wg---worki… 15 \| [Training](https://gitter.im/onnx/training) \| Expand ONNX to support training as well as inferenc… 16 …ONNX models to edge platforms by identifying the ONNX operators that must be supported by mobile a… 23 …video/image processing \| Completed - If, Loop, and Scan operators were added in ONNX 1.3 release. \| 24 …on) \| Enhance ONNX to support quantized data types and operators on a variety of runtimes and hard… 30 …reate tools, tests and APIs to ensure models and backends comply with the ONNX specification \| bec…
/dports/misc/py-onnx/onnx-1.10.2/onnx.egg-info/
H A D	PKG-INFO	`6 Author: ONNX 29 # Use ONNX 30 * [Tutorials for creating ONNX models](https://github.com/onnx/tutorials). 31 * [Pre-trained ONNX models](https://github.com/onnx/models) 33 # Learn about the ONNX spec 35 * [ONNX intermediate representation spec][ir] 40 # Programming utilities for working with ONNX Graphs 67 ONNX released packages are published in PyPi. 86 ## Build ONNX from Source 142 ### Build ONNX on ARM 64 [all …]`
/dports/misc/py-onnx/onnx-1.10.2/
H A D	PKG-INFO	`6 Author: ONNX 29 # Use ONNX 30 * [Tutorials for creating ONNX models](https://github.com/onnx/tutorials). 31 * [Pre-trained ONNX models](https://github.com/onnx/models) 33 # Learn about the ONNX spec 35 * [ONNX intermediate representation spec][ir] 40 # Programming utilities for working with ONNX Graphs 67 ONNX released packages are published in PyPi. 86 ## Build ONNX from Source 142 ### Build ONNX on ARM 64 [all …]`
/dports/graphics/opencv/opencv-4.5.3/cmake/
H A D	FindONNX.cmake	`3 set(ONNXRT_ROOT_DIR "" CACHE PATH "ONNX Runtime install directory") 22 set(ONNX_LIBRARIES "${ORT_LIB}" CACHE STRING "ONNX Runtime libraries") 23 set(ONNX_INCLUDE_DIR "${ORT_INCLUDE}" CACHE STRING "ONNX Runtime include path") 26 set(ONNX_LIBRARY "onnxruntime" CACHE STRING "ONNX Link Target")`
/dports/misc/glow/glow-f24d960e3cc80db95ac0bc17b1900dbf60ca044a/thirdparty/onnx/docs/proposals/
H A D	NLPinONNXproposal.md	3 … fairly non-uniformly across the landscape of frameworks. The ability for ONNX to interchange thes… 9 …ntly complex that supporting it will push forward the state of the art in ONNX, but not so complex… 16 * Requirements from an ONNX representation 34 …ture that we can break down into incremental improvements to ONNX without compromising ONNX's fund… 48 …Multiplicative Integration LSTM (https://arxiv.org/pdf/1606.06630.pdf) in ONNX. We can expose a st… 50 …ow operators in ONNX, however, fulfill all of these requirements, and thus we can represent many i… 57 …ONNX. Facebook is currently working on this internally and creating a pytorch→ONNX→caffe2 pathway.… 61 …ps://arxiv.org/abs/1602.07776). These will present further challenges for ONNX, and the representa… 63 …okens to indices. Initially this will probably remain out of the scope of ONNX unless there is a g… 67 …ONNX, using seq2seq with attention as a canonical example that covers many use cases. We would lik…
H A D	ONNXIFIproposal.md	1 # ONNX Interface for Framework Integration: API Proposal 7 …ONNX format targets the problem of offline conversion of neural network models between different h… 14 …al network model (either in ONNX format, or in the format of their deep learning framework, and co… 21 - Neural network graphs are passed as serialized ONNX ModelProto messages. To avoid serialization o… 25 - There is no minimal set of ONNX operators to implement. The implementer and the user (a deep lear… 34 * Query if a backend supports an ONNX operator with particular parameters and input shapes (`onnxGe… 35 * Convert an ONNX graph to opaque vendor-specific representation of a backend (`onnxInitGraph`) 37 * Run an ONNX graph, converted to vendor-specific representation (`onnxRunGraph`) 42 …ramework) iterates operators in a model graph one-by-one, convert them to ONNX, and calls `onnxGet… 55 4. The user initialized the backend, and offloads the subgraph execution to the ONNX backend by cal… [all …]

12 3 4 5 6 7 8 9 10 >>...12