Comments (4)
I just tried to reproduce this on the head of TKML source code, and couldn't. My guess is the bug was in tkml 1.1.2 but has already been fixed. Let's monitor for the bug the next time we make a big report.
On head of tkml:
Info: The stats for ~/.cache/turnkey\linear_selftest_76af2f62\turnkey_stats.yaml are:
author: selftest
builtin_model_script: https://github.com/onnx/turnkeyml/tree/cbd3abc173b4bc93d06131f6199d08ef2f6bc143/models/selftest/linear.py
class: LinearTestModel
evaluations:
57651c20:
benchmark_status: not_started
build_status: error
device_type: x86
error_log: "Exporting PyTorch to ONNX\nTraceback (most recent call last):\n File\
\ \"C:\\work\\turnkeyml\\src\\turnkeyml\\build\\stage.py\", line 135, in fire_helper\n\
\ state = self.fire(state)\n File \"C:\\work\\turnkeyml\\src\\turnkeyml\\\
build\\export.py\", line 224, in fire\n raise ValueError(\"Gotcha\")\nValueError:\
\ Gotcha"
iterations: 100
runtime: ort
selected_sequence_of_stages:
- export_pytorch
- optimize_onnx
stage_duration:export_pytorch: 0.3145256042480469
stage_duration:optimize_onnx: '-'
stage_status:export_pytorch: error
stage_status:optimize_onnx: not_started
The benchmark_status is correctly set to "not started"
from turnkeyml.
Related Issues (20)
- Turnkey stats evaluation ID collisions HOT 1
- Provide an option to use a fully-standardized conda environment HOT 2
- Add error messages to report.csv
- Use full-sized GPT-J
- Create an ORT base class and refactor run/onnxrt on to it
- Configurable verbosity in Analyzer Status HOT 1
- Change `--rebuild` to `--skip` HOT 5
- Integrate mass-benchmarking into the Files API HOT 3
- Validate `benchmark_files()` arguments
- turnkey hangs on querying OEM system information
- Input size is only saved to stats in ONNX tool flows
- Proposal: check model path in `--model_path` scripts
- Enhance conda creation methodology for onnxrt
- `stage_status = killed` has no `error_log` message HOT 1
- Proposal: Store tkml CLI command and timestamp as part of stats and report
- Proposal: A way to skip LLMs
- Issue with converting to ONNX format for LLM models HOT 3
- Stage durations are not being correctly recorded
- Fix CI and enable TKML to work with torch >= 2.2.0
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from turnkeyml.