Comments (2)
How much different do you see? It is expected that they are not exactly same.
from onnxruntime.
log-softmax score difference - upper bound 1e-1
When applying dynamic quantization, I expected there would be some degree of difference. However, with static quantization, shouldn't all values be fixed, yielding the same results regardless of cpu architecture? Is it possible to eliminate differences by adjusting the calibration data or the ONNX Runtime quantization options?
from onnxruntime.
Related Issues (20)
- BeamSearch op returning wrong results on CUDA execution provider when sequence is used as input_ids HOT 1
- [Documentation] ORT Format Model Version Table Needs Update HOT 2
- [Mobile] Broadcasting Error in Sub Node with ONNX Runtime Version 1.17.3: Incompatibility with Dimension Broadcasting Rules
- Type Error: Type 'tensor(int64)' of input parameter (16586) of operator (Clip) in node (Clip_13292) is invalid. HOT 4
- LayerNormalization doesnt' work as expected in MAC.
- User-provided session logging function is not used for every log HOT 4
- NOT_IMPLEMENTED : Could not find an implementation for ReduceProd(18) node with name 'p2o.ReduceProd.0'
- [Performance] Quadratic behaviour in list operations with SequenceInsert in onnx
- [Build] [CANN] Failed to build CANN provider with training and Python bindings
- ONNX Runtime doesn't support the graph optimization of vision-encoder-decoder yet
- cannot resolve operator 'HardSwish' with opsets: ai.onnx v9 [Web]
- cuda's FusedConv is not support Sigmod
- [Mobile] Subgraphs duplicate initializers in RAM during execution HOT 1
- [Web] The YOLOv8 segmentation model with batching option is not runing on the GPU ? HOT 2
- [Performance] Regression observed when using CUDA execution provider HOT 15
- Onnxruntime-directml 1.18.0 broken multithreading inference session HOT 3
- [Build] 0.18.0 release breaks Hummingbird build pipeline HOT 4
- Windows ARM64 & X64 CLIP Image Encoder different results HOT 2
- .. HOT 1
- [Feature Request] Get device ids via get_available_device_ids()
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 onnxruntime.