Comments (3)
Loading untrusted PyTorch tensors is a security risk. So I'm not going to try and reproduce your results.
Have you tried specifying compute_precision=ct.precision.FLOAT32
in your ct.convert
call? Your code is not setting that. So your Core ML model is most likely using float16 while your PyTorch model is most likely using float32. This would explain why you're getting overflow in your Core ML model but not your PyTorch model.
from coremltools.
@TobyRoseman
Thank you so much for your help.
It works with the setting compute_precision=ct.precision.FLOAT32
Best,
Xiaohui
from coremltools.
Thanks for letting us know. I'm going to close this issue.
from coremltools.
Related Issues (20)
- index_put failing when indices are bool type HOT 1
- CI Github macos ARM HOT 2
- Easy way to determine which graph passes get applied
- Experiencing "divided by two must all be the same length" when trying to convert a PyTorch MaxPool2d
- XlaCallModule or another way of loading StableHLO code HOT 4
- How do I trace back to offending network-layer in my python code when an error occurs during CoreML-conversion
- Refactor PyTorch 64-Bit Data Type Conversion HOT 2
- The peculiar behavior of matrix multiplication. HOT 4
- Error Converting Minimal DETR Implementation - I think it originates from torch.nn.Transformer() HOT 7
- (op_type: inverse) Input x="1308" expects tensor or scalar of dtype from type domain ['fp16', 'fp32'] but got tensor[1,int32] HOT 1
- How to convert YOLOX model with proper output structure HOT 1
- When I convert the yolo world to coreml, I found I can only customized less than 8 class label. HOT 1
- AttributeError during conversion with flexible shape HOT 4
- AttributeError: 'list' object has no attribute 'val' HOT 2
- HUGS support from CoreML? HOT 5
- official CoreML Unity plugin for Unity Polyspatial visionOS? HOT 1
- Result of Flexible-input-shape Model is NAN HOT 4
- [Optimize] [ExecuTorch] [CoreMLQuantizer] Support `int8` and `uint8` in addition to `qint8` and `quint8`
- How to know a Core ML Model been added image preprocessing options? HOT 1
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 coremltools.