Comments (6)
@iou2much thanks, @leixiaoning please help check this
from athena.
@iou2much thanks, @leixiaoning please help check this
ok, i will check. @tjadamlee
from athena.
Hi. We want to use it in mix-precisioned mode, as our GPU don't have much memory, and we want to speed up the training.
I change the code to use mix-precisioned training feature in TF2. It works for MPC (stage 1).
But for the fine-tuning stage, the loss becomes nan at the very beginning.
I try to debug it, and find out the PositionalEncoding in speech_transformer.py is always returning NaN.input_labels = layers.Input(shape=data_descriptions.sample_shape["output"], dtype=tf.int32) inner = layers.Embedding(self.num_class, d_model)(input_labels) inner = PositionalEncoding(d_model, scale=True)(inner) #it returns NaN inner = layers.Dropout(self.hparams.rate)(inner) self.y_net = tf.keras.Model(inputs=input_labels, outputs=inner, name="y_net")
could anyone help? Thanks a lot
did you use os.environ['TF_ENABLE_AUTO_MIXED_PRECISION'] = '1' for supporting mixed precision training? @iou2much
from athena.
nope. I add this before the model initialization.
tf.keras.mixed_precision.experimental.set_policy('mixed_float16')
from athena.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
from athena.
This issue is closed. You can also re-open it if needed.
from athena.
Related Issues (20)
- training and decoding time HOT 2
- Can the authors provide pretrained weights?? HOT 2
- TensorArray Bug HOT 2
- Issue in Athena Insatllation HOT 2
- Beam Search: the initial cand paraent should be sos
- Beam Search Bug: new_states are rewritten by the last scorer HOT 2
- Example audio? HOT 2
- There is a problem when testing my installation HOT 2
- Questions about the implementation of GLU HOT 3
- Performance issue in thr program HOT 2
- meet an issue when i run the tools/env.sh HOT 2
- setup.py shutil.copy fail permission Error HOT 2
- dataset for speech simclr HOT 2
- Speech Emotion Recognition Pipeline HOT 2
- How to convert a audio file to text file? HOT 1
- The delta pitch feature seems to be strange HOT 4
- Vocabularies with no concepts still existing
- 运行失败 HOT 3
- Ask for Didispeech Dataset
- To add the pack_content table to the release batch 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 athena.