{"id":16107897,"url":"https://github.com/fl33tw00d/steelix","last_synced_at":"2025-03-16T08:32:35.749Z","repository":{"id":61447129,"uuid":"536102642","full_name":"FL33TW00D/steelix","owner":"FL33TW00D","description":"Your one stop CLI for ONNX model analysis.","archived":false,"fork":false,"pushed_at":"2022-11-13T14:30:45.000Z","size":3599,"stargazers_count":47,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-07T17:56:35.111Z","etag":null,"topics":["flops-counter","machine-learning","onnx","visualization"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FL33TW00D.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-09-13T11:54:30.000Z","updated_at":"2025-01-22T14:35:05.000Z","dependencies_parsed_at":"2023-01-21T17:15:47.004Z","dependency_job_id":null,"html_url":"https://github.com/FL33TW00D/steelix","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FL33TW00D%2Fsteelix","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FL33TW00D%2Fsteelix/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FL33TW00D%2Fsteelix/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FL33TW00D%2Fsteelix/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FL33TW00D","download_url":"https://codeload.github.com/FL33TW00D/steelix/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243806071,"owners_count":20350775,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["flops-counter","machine-learning","onnx","visualization"],"created_at":"2024-10-09T19:24:46.438Z","updated_at":"2025-03-16T08:32:34.817Z","avatar_url":"https://github.com/FL33TW00D.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003cimg width=\"400px\" height=\"200px\" src=\"https://github.com/FL33TW00D/steelix/raw/master/.github/images/SteelixLogo.png\"\u003e\n\u003c/div\u003e\n\u003cp align=\"center\"\u003eYour one stop CLI for \u003cb\u003eONNX\u003c/b\u003e model analysis. \u003cbr\u003e\u003c/br\u003e Featuring graph visualization, FLOP counts, memory metrics and more!\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n \u003ca href=\"https://crates.io/crates/steelix\"\u003e\n \u003cimg alt=\"GitHub\" src=\"https://img.shields.io/github/license/FL33TW00D/steelix.svg?color=blue\"\u003e\n \u003c/a\u003e\n \u003ca href=\"https://huggingface.co/docs/transformers/index\"\u003e\n \u003cimg alt=\"crates.io\" src=\"https://img.shields.io/crates/v/steelix.svg\"\u003e\n \u003c/a\u003e\n \u003ca href=\"https://github.com/FL33TW00D/steelix/releases\"\u003e\n \u003cimg alt=\"GitHub release\" src=\"https://img.shields.io/github/release/FL33TW00D/steelix.svg\"\u003e\n \u003c/a\u003e\n\u003c/p\u003e\n\n## ⚡️ Quick start\nFirst, [download](https://graphviz.org/download/) and install DOT.\nInstallation can be done via `cargo`:\n\n```bash\ncargo install steelix\n```\nMacOS users can also install via HomeBrew:\n\n```bash\nbrew tap FL33TW00D/steelix\nbrew install steelix\n```\n\n## ⚙️ Commands \u0026 Options\nSteelix has 2 core functions - model summarization \u0026 model visualization.\n\n### `summary`\n\nCLI command to summarize the core aspects of your model.\n\n```bash\nsteelix summary --model-path ./my-model.onnx\n```\n| Option | Description | Type | Default | Required? |\n|------------------|----------------------------------------------------------|--------|---------|-----------|\n| `--model-path` | Path at which your model is located. | `bool` | `false` | No |\n\n\n\u003cimg width=\"700px\" src=\"https://github.com/FL33TW00D/steelix/raw/master/.github/images/steelix_summary.gif\"\u003e\n\n### `plot`\n\nCLI command to plot your model as an SVG file - complete with inferred shapes.\n\n```bash\nsteelix plot --model-path ./my-model.onnx --open \n```\n\n| Option | Description | Type | Default | Required? |\n|--------------------|---------------------------------------|-----------|---------------|-----------|\n| `--model-path` | Path at which your model is located. | `string` | None | Yes |\n| `--output-path` | Path at which your SVG will be saved. | `string` | `./model.svg` | No |\n| `--open` | Open SVG in browser once generated. | `boolean` | `false` | No |\n| `--disable-shapes` | Disable shape inference. | `boolean` | `false` | No |\n\n\u003cimg width=\"700px\" src=\"https://github.com/FL33TW00D/steelix/raw/master/.github/images/steelix_plot.gif\"\u003e\n\n\n## Supported Operators (ref [ONNX IR](https://github.com/onnx/onnx/blob/master/docs/Operators.md?plain=1)) \n\n| **Operator** | **Implemented** |\n|---------------------------|--------------------------------------|\n| Abs | ✅ |\n| Acos | |\n| Acosh | |\n| Add | ✅ |\n| And | |\n| ArgMax | |\n| ArgMin | |\n| Asin | |\n| Asinh | |\n| Atan | |\n| Atanh | |\n| AveragePool | |\n| BatchNormalization | ✅ |\n| BitShift | |\n| Cast | |\n| Ceil | |\n| Clip | |\n| Compress | |\n| Concat | ✅ |\n| ConcatFromSequence | |\n| Constant | |\n| ConstantOfShape | |\n| Conv | ✅ |\n| ConvInteger | |\n| ConvTranspose | |\n| Cos | |\n| Cosh | |\n| CumSum | |\n| DepthToSpace | |\n| DequantizeLinear | |\n| Det | |\n| Div | |\n| Dropout | |\n| Einsum | |\n| Elu | |\n| Equal | |\n| Erf | ✅ |\n| Exp | |\n| Expand | |\n| EyeLike | |\n| Flatten | |\n| Floor | |\n| GRU | |\n| Gather | ✅ |\n| GatherElements | |\n| GatherND | |\n| Gemm | ✅ |\n| GlobalAveragePool | |\n| GlobalLpPool | |\n| GlobalMaxPool | |\n| Greater | |\n| GridSample | |\n| HardSigmoid | |\n| Hardmax | |\n| Identity | |\n| If | |\n| InstanceNormalization | |\n| IsInf | |\n| IsNaN | |\n| LRN | |\n| LSTM | |\n| LeakyRelu | ✅ |\n| Less | |\n| Log | |\n| Loop | |\n| LpNormalization | |\n| LpPool | |\n| MatMul | ✅ |\n| MatMulInteger | |\n| Max | |\n| MaxPool | ✅ |\n| MaxRoiPool | |\n| MaxUnpool | |\n| Mean | |\n| Min | |\n| Mod | |\n| Mul | ✅ |\n| Multinomial | |\n| Neg | |\n| NonMaxSuppression | |\n| NonZero | |\n| Not | ✅ |\n| OneHot | |\n| Optional | |\n| OptionalGetElement | |\n| OptionalHasElement | |\n| Or | |\n| PRelu | |\n| Pad | ✅ (mode=constant, pads\u003e=0) |\n| Pow | |\n| QLinearConv | |\n| QLinearMatMul | |\n| QuantizeLinear | |\n| RNN | |\n| RandomNormal | |\n| RandomNormalLike | |\n| RandomUniform | |\n| RandomUniformLike | |\n| Reciprocal | |\n| ReduceL1 | |\n| ReduceL2 | |\n| ReduceLogSum | |\n| ReduceLogSumExp | |\n| ReduceMax | |\n| ReduceMean | |\n| ReduceMin | |\n| ReduceProd | |\n| ReduceSum | |\n| ReduceSumSquare | |\n| Relu | ✅ |\n| Reshape | ✅ |\n| Resize | |\n| ReverseSequence | |\n| RoiAlign | |\n| Round | |\n| Scan | |\n| Scatter (deprecated) | |\n| ScatterElements | |\n| ScatterND | |\n| Selu | |\n| SequenceAt | |\n| SequenceConstruct | |\n| SequenceEmpty | |\n| SequenceErase | |\n| SequenceInsert | |\n| SequenceLength | |\n| Shape | |\n| Shrink | |\n| Sigmoid | ✅ |\n| Sign | |\n| Sin | |\n| Sinh | |\n| Size | |\n| Slice | |\n| Softplus | |\n| Softsign | |\n| SpaceToDepth | |\n| Split | |\n| SplitToSequence | |\n| Sqrt | |\n| Squeeze | ✅ |\n| StringNormalizer | |\n| Sub | |\n| Sum | |\n| Tan | |\n| Tanh | |\n| TfIdfVectorizer | |\n| ThresholdedRelu | |\n| Tile | |\n| TopK | |\n| Transpose | |\n| Trilu | |\n| Unique | |\n| Unsqueeze | ✅ |\n| Upsample (deprecated) | |\n| Where | |\n| Xor | |\n| **Function** | |\n| Bernoulli | |\n| CastLike | |\n| Celu | |\n| DynamicQuantizeLinear | |\n| GreaterOrEqual | |\n| HardSwish | |\n| LessOrEqual | |\n| LogSoftmax | |\n| MeanVarianceNormalization | |\n| NegativeLogLikelihoodLoss | |\n| Range | |\n| Softmax | ✅ |\n| SoftmaxCrossEntropyLoss | |\n\n\n## Credit\nMost of the good ideas/code in this project are **heavily** inspired by [tract](https://github.com/sonos/tract), [wonnx](https://github.com/webonnx/wonnx) or [netron](https://github.com/lutzroeder/netron).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffl33tw00d%2Fsteelix","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffl33tw00d%2Fsteelix","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffl33tw00d%2Fsteelix/lists"}