Skip to content

Commit 46d2b76

Browse files
RouxJohannesRouxJohannes
committed
README update
1 parent b24e2a8 commit 46d2b76

File tree

1 file changed

+46
-24
lines changed

1 file changed

+46
-24
lines changed

‎README.md‎

Lines changed: 46 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -11,41 +11,51 @@ repository. If you are actively using this repository and want to report any iss
1111

1212
The latest version of the documentation for the Poplar software stack, and other developer resources, is available at https://www.graphcore.ai/developer.
1313

14-
> The code presented here requires using Poplar SDK 2.3.x
14+
> The code presented here requires using Poplar SDK 2.4.x
1515
1616
Please install and enable the Poplar SDK following the instructions in the Getting Started guide for your IPU system.
1717

1818
Unless otherwise specified by a LICENSE file in a subdirectory, the LICENSE referenced at the top level applies to the files in this repository.
1919

2020
## Repository contents
2121

22-
### Notable examples
23-
24-
| Example | Link |
25-
| ------- | ---- |
26-
| BERT (PopART) | [code](applications/popart/bert) |
27-
| BERT (TensorFlow) | [code](applications/tensorflow/bert) |
28-
| BERT (PyTorch) | [code](applications/pytorch/bert) |
29-
| DeepVoice3 speech synthesis (PopART) | [code](applications/popart/deep_voice) |
30-
| Conformer speech recognition (PopART) | [code](applications/popart/conformer_asr) |
31-
| CNN Training including ResNet, ResNeXt & EfficientNet (TensorFlow) | [code](applications/tensorflow/cnns/training) |
32-
| CNN Inference including ResNet, MobileNet & EfficientNet (TensorFlow) | [code](applications/tensorflow/cnns/inference) |
33-
| CNN Training & Inference including ResNet, ResNeXt & EfficientNet (PyTorch) | [code](applications/pytorch/cnns) |
34-
| Yolo v3 Object Detection (TensorFlow) | [code](applications/tensorflow/detection) |
35-
| ResNext Inference (PopART) | [code](applications/popart/resnext_inference) |
36-
| Recommendation using Autoencoders (TensorFlow) | [code](applications/tensorflow/autoencoder) |
37-
| Sales forecasting example (TensorFlow) | [code](applications/tensorflow/sales_forecasting) |
38-
| Contrastive Divergence VAE using MCMC methods (TensorFlow) | [code](applications/tensorflow/contrastive_divergence_vae) |
39-
| Example reinforcement learning policy model (TensorFlow)| [code](applications/tensorflow/reinforcement_learning) |
40-
| Click through rate: Deep Interest Network (TensorFlow) | [code](applications/tensorflow/click_through_rate) |
41-
| Click through rate: Deep Interest Evolution Network (TensorFlow) | [code](applications/tensorflow/click_through_rate) |
42-
| Dynamic Sparsity: MNIST RigL (TensorFlow) | [code](applications/tensorflow/dynamic_sparsity/mnist_rigl) |
43-
| Dynamic Sparsity: Autoregressive Language Modelling (TensorFlow) | [code](applications/tensorflow/dynamic_sparsity/language_modelling) |
44-
4522
### Application examples
4623

4724
The [applications/](applications) folder contains example applications written in different frameworks targeting the IPU. See the READMEs in each folder for details on how to use these applications.
4825

26+
| Model | Domain | Type |Links |
27+
| ------- | ------- |------- | ------- |
28+
| ResNet | Image Classifcation | Training & Inference | [TensorFlow 1](applications/tensorflow/cnns/) , [TensorFlow 2](applications/tensorflow/cnns/), [PyTorch](applications/pytorch/cnns/)|
29+
| ResNeXt | Image Classifcation | Training & Inference | [TensorFlow 1](applications/tensorflow/cnns/) , [PopART (Inference)](applications/popart/resnext_inference)
30+
| EfficientNet | Image Classifcation | Training & Inference | [TensorFlow 1](applications/tensorflow/cnns/) , [PyTorch](applications/pytorch/cnns/)|
31+
| MobileNet | Image Classifcation | Inference | [TensorFlow 1](applications/tensorflow/cnns/inference) |
32+
| MobileNetv2 | Image Classifcation | Inference | [TensorFlow 1](applications/tensorflow/cnns/inference) |
33+
| MobileNetv3 | Image Classifcation | Training & Inference | [PyTorch](applications/tensorflow/cnns/) |
34+
| ViT(Vision Transformer) | Image Classifcation | Training| [PyTorch](applications/pytorch/vit) |
35+
| Yolov3 | Object Detection | Training & Inference | [TensorFlow 1](applications/tensorflow/detection/yolov3) |
36+
| Yolov4-P5 | Object Detection | Inference | [PyTorch](applications/pytorch/detection) |
37+
| Faster RCNN | Object Detection | Training & Inference | [PopART](applications/popart/faster-rcnn) |
38+
| UNet (Medical) | Image segmentation | Training & Inference | [TensorFlow 2](applications/tensorflow2/unet/) |
39+
| miniDALL-E | Generative model in Vision | Training & Inference | [PyTorch](applications/pytorch/miniDALL-E) |
40+
| BERT | NLP | Training & Inference |[TensorFlow 1](applications/tensorflow/bert) , [PyTorch](applications/pytorch/bert) , [PopART](applications/popart/bert), [TensorFlow 2](applications/tensorflow2/bert)|
41+
| DeepVoice3 | TTS (TextToSpeech) | Training & Inference |[PopART](applications/popart/deep_voice) |
42+
| FastSpeech2 | TTS(TextToSpeech) | Training & Inference | [TensorFlow 2](applications/tensorflow2/fastspeech2/) |
43+
| Conformer | STT(SpeechToText) | Training & Inference | [PopART](applications/popart/conformer_asr) |
44+
| Conformer with Transformer | STT(SpeechToText) | Training & Inference | [TensorFlow 1](applications/tensorflow/conformer) |
45+
| Transfomer Transducer | STT(SpeechToText) | Training & Inference | [PopART](applications/popart/transformer_transducer) |
46+
| TGN (Temporal Graph Network) | GNN | Training & Inference | [TensorFlow 1](applications/tensorflow/tgn/) |
47+
| MPNN (Message Passing Neural Networks) | GNN | Training & Inference | [TensorFlow 2](code_examples/tensorflow2/message_passing_neural_network) |
48+
| Deep AutoEncoders for Collaborative Filtering | Recommender Systems | Training & Inference | [TensorFlow 1](applications/tensorflow/autoencoder) |
49+
| Click through rate: Deep Interest Network | Recommender Systems | Training & Inference | [TensorFlow 1](applications/tensorflow/click_through_rate) |
50+
| Click through rate: Deep Interest Evolution Network | Recommender Systems | Training & Inference | [TensorFlow 1](applications/tensorflow/click_through_rate) |
51+
| RL Policy model | Reinforcement Learning | Training | [TensorFlow 1](applications/tensorflow/reinforcement_learning) |
52+
| MNIST RigL | Dynamic Sparsity | Training | [TensorFlow 1](applications/tensorflow/dynamic_sparsity/mnist_rigl) |
53+
| Autoregressive Language Modelling | Dynamic Sparsity | Training | [TensorFlow 1](applications/tensorflow/dynamic_sparsity/language_modelling) |
54+
| Sales forecasting | MLP (Multi-Layer Perceptron) | Training | [TensorFlow 1](applications/tensorflow/dynamic_sparsity/language_modelling) |
55+
| Contrastive Divergence VAE using MCMC methods | Generative Model | Training | [TensorFlow 1](applications/tensorflow/contrastive_divergence_vae) |
56+
| Monte Carlo Ray Tracing | Vision | Inference | [Poplar](applications/poplar/monte_carlo_ray_tracing) |
57+
58+
4959
### Code examples
5060

5161
The [code_examples/](code_examples) folder contains smaller models and code examples. See the READMEs in each folder for details.
@@ -60,3 +70,15 @@ The [utils/](utils) folder contains utilities libraries and scripts that are use
6070

6171
* [utils/examples_tests](utils/examples_tests) - Common Python helper functions for the repository's unit tests.
6272
* [utils/benchmarks](utils/benchmarks) - Common Python helper functions for running benchmarks on the IPU in different frameworks.
73+
74+
75+
## Changelog
76+
77+
December 2021:
78+
- Added those models below to reference models
79+
- Vision : miniDALL-E(PyTorch), Faster RCNN(PopART), UNet(TensorFlow 2), ResNet50(TensorFlow 2)
80+
- NLP : BERT(TensorFlow 2)
81+
- TTS/STT : FastSpeech2(TensorFlow 2), Transfomer Transducer(PopART), Conformer with Transformer(PyTorch)
82+
- GNN : TGN(TensorFlow1), MPNN(TensorFlow 2)
83+
84+

0 commit comments

Comments
 (0)