Comments (7)
raziel
commented on May 22, 2024
Not that we know of. I don't believe the open source bert trainer uses Keras. It would beb nice to see somebody trying it out though.
from model-optimization.
alanchiao
commented on May 22, 2024
@haozha111 is trying this out
from model-optimization.
Jasperty
commented on May 22, 2024
how to apply this api to bert? do you train bert by keras? can we use bert trained by tensorflow?
from model-optimization.
haozha111
commented on May 22, 2024
The pruning API only supports keras model right now. I'm just starting to trying it out, and don't have any code examples now. Will post here once I get some good results. Thanks!
from model-optimization.
teijeong
commented on May 22, 2024
Hi @haozha111, is there some updates?
from model-optimization.
lan2720
commented on May 22, 2024
The pruning API only supports keras model right now. I'm just starting to trying it out, and don't have any code examples now. Will post here once I get some good results. Thanks!
Hi @haozha111, is there some updates?
from model-optimization.
haozha111
commented on May 22, 2024
no, I haven't tried it recently. if you are interested, please follow docs in https://www.tensorflow.org/model_optimization to apply it to BERT, also cc'ing Jaesung who is currently working on MOT.
from model-optimization.
Related Issues (20)
- Determinism is not yet supported in GPU implementation of FakeQuantWithMinMaxVarsGradient HOT 2
- batch norm layer quantization error HOT 2
- 16x8 Quantization fails for RNN model - Max and min for dynamic tensors should be recorded during calibration HOT 4
- float16 quantization runs out of memory for LSTM model HOT 3
- float16 quantization runs out of memory for LSTM model HOT 1
- Add a default PruningPolicy that filters out any layers not supported by the API HOT 1
- Add batch norm to default_n_bit_quantize_registry and default_8_bit_quantize_registry HOT 2
- Quant aware training in tensorflow model optimization HOT 4
- [COLAB] No module named 'tensorflow_model_optimization' HOT 1
- Module Import Error HOT 2
- A error about quantization aware training HOT 2
- MobileNetV3 QAT TFLite Conversion Issue HOT 4
- Error in MovingAverageQuantizer with per_axis=True due to missing parameters in _add_range_weights
- strange behavior when quantizing a model. HOT 2
- Support for Recurrent layers for Quantization Aware Training. HOT 1
- Can't use TFMOT version 0.8.0 due to missing dependency HOT 1
- Any plans to support keras3? HOT 3
- Cannot use Quantize layer and use abstract class and methods HOT 1
- Custom layer with Concat afterwards causes an error during QAT modeling HOT 3
- Failed quantization of dilated convolution layers: tensorflow or tensorflow-model-optimization bug?
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 model-optimization.