Skip to content

Commit dcc423b

Browse files
Mahathi-VatsalMahathi-Vatsal
authored
Refactored tensorflow cpu workloads (#2561)
* Refactored_tf * Fixed compliance issue
1 parent e374b13 commit dcc423b

File tree

124 files changed

+235
-4527
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

124 files changed

+235
-4527
lines changed

Diff for: ‎README.md

+10-10
Original file line numberDiff line numberDiff line change
@@ -50,8 +50,8 @@ For best performance on Intel® Data Center GPU Flex and Max Series, please chec
5050

5151
| Model | Framework | Mode | Model Documentation | Benchmark/Test Dataset |
5252
| ------------------------------------------------------ | ---------- | ----------| ------------------- | ---------------------- |
53-
| [ResNet 50v1.5](https://github.com/tensorflow/models/tree/v2.11.0/official/legacy/image_classification/resnet) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | TensorFlow | Inference | [Int8 FP32 BFloat16 BFloat32](/quickstart/image_recognition/tensorflow/resnet50v1_5/inference/cpu/README.md) | [ImageNet 2012](https://github.com/IntelAI/models/tree/master/datasets/imagenet/README.md) |
54-
| [ResNet 50v1.5](https://github.com/tensorflow/models/tree/v2.11.0/official/legacy/image_classification/resnet) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | TensorFlow | Training | [FP32 BFloat16 BFloat32](/quickstart/image_recognition/tensorflow/resnet50v1_5/training/cpu/README.md) | [ImageNet 2012](https://github.com/IntelAI/models/tree/master/datasets/imagenet/README.md) |
53+
| [ResNet 50v1.5](https://github.com/tensorflow/models/tree/v2.11.0/official/legacy/image_classification/resnet) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | TensorFlow | Inference | [Int8 FP32 BFloat16 BFloat32](/models_v2/tensorflow/resnet50v1_5/inference/cpu/README.md) | [ImageNet 2012](https://github.com/IntelAI/models/tree/master/datasets/imagenet/README.md) |
54+
| [ResNet 50v1.5](https://github.com/tensorflow/models/tree/v2.11.0/official/legacy/image_classification/resnet) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | TensorFlow | Training | [FP32 BFloat16 BFloat32](/models_v2/tensorflow/resnet50v1_5/training/cpu/README.md) | [ImageNet 2012](https://github.com/IntelAI/models/tree/master/datasets/imagenet/README.md) |
5555
| [ResNet 50](https://arxiv.org/pdf/1512.03385.pdf) | PyTorch | Inference | [Int8 FP32 BFloat16 BFloat32](/models_v2/pytorch/resnet50/inference/cpu/README.md) | [ImageNet 2012] |
5656
| [ResNet 50](https://arxiv.org/pdf/1512.03385.pdf) | PyTorch | Training | [FP32 BFloat16 BFloat32](/models_v2/pytorch/resnet50/training/cpu/README.md) | [ImageNet 2012] |
5757
| [Vision Transformer](https://huggingface.co/google/vit-base-patch16-224) | PyTorch | Inference | [FP32 BFloat16 BFloat32 FP16 INT8](/models_v2/pytorch/vit/inference/cpu/README.md) | [ImageNet 2012] |
@@ -60,15 +60,15 @@ For best performance on Intel® Data Center GPU Flex and Max Series, please chec
6060

6161
| Model | Framework | Mode | Model Documentation | Benchmark/Test Dataset |
6262
| -------------------------------------------------------- | ---------- | ----------| ------------------- | ---------------------- |
63-
| [3D U-Net](https://arxiv.org/pdf/1606.06650.pdf) | TensorFlow | Inference | [FP32 BFloat16 Int8](/benchmarks/image_segmentation/tensorflow/3d_unet/inference/README.md) | [BRATS 2018](https://www.med.upenn.edu/sbia/brats2018/registration.html) |
63+
| [3D U-Net](https://arxiv.org/pdf/1606.06650.pdf) | TensorFlow | Inference | [FP32 BFloat16 Int8](/models_v2/tensorflow/3d_unet/inference/cpu/README.md) | [BRATS 2018](https://www.med.upenn.edu/sbia/brats2018/registration.html) |
6464

6565
### Language Modeling
6666

6767
| Model | Framework | Mode | Model Documentation | Benchmark/Test Dataset |
6868
| -------------------------------------------- | ---------- | ----------| ------------------- | ---------------------- |
69-
| [BERT large](https://arxiv.org/pdf/1810.04805.pdf) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | Tensorflow | Inference | [FP32 BFloat16 Int8 BFloat32](/quickstart/language_modeling/tensorflow/bert_large/inference/cpu/README.md) | [SQuAD](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#inference) |
70-
| [BERT large](https://arxiv.org/pdf/1810.04805.pdf) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | Tensorflow | Training | [FP32 BFloat16 BFloat32](/quickstart/language_modeling/tensorflow/bert_large/training/cpu/README.md) | [SQuAD](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#inference) |
71-
| [BERT large (Hugging Face)](https://arxiv.org/pdf/1810.04805.pdf) | TensorFlow | Inference | [FP32 FP16 BFloat16 BFloat32](/benchmarks/language_modeling/tensorflow/bert_large_hf/inference/README.md) | [SQuAD](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#inference) |
69+
| [BERT large](https://arxiv.org/pdf/1810.04805.pdf) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | Tensorflow | Inference | [FP32 BFloat16 Int8 BFloat32](/models_v2/tensorflow/bert_large/inference/cpu/README.md) | [SQuAD](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#inference) |
70+
| [BERT large](https://arxiv.org/pdf/1810.04805.pdf) [Sapphire Rapids](https://www.intel.com/content/www/us/en/newsroom/opinion/updates-next-gen-data-center-platform-sapphire-rapids.html#gs.blowcx) | Tensorflow | Training | [FP32 BFloat16 BFloat32](/models_v2/tensorflow/bert_large/training/cpu/README.md) | [SQuAD](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#inference) |
71+
| [BERT large (Hugging Face)](https://arxiv.org/pdf/1810.04805.pdf) | TensorFlow | Inference | [FP32 FP16 BFloat16 BFloat32](/models_v2/tensorflow/bert_large_hf/inference/cpu/README.md) | [SQuAD](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#inference) |
7272
| [BERT large](https://arxiv.org/pdf/1810.04805.pdf) | PyTorch | Inference | [FP32 Int8 BFloat16 BFloat32](/models_v2/pytorch/bert_large/inference/cpu/README.md) | BERT Large SQuAD1.1 |
7373
| [BERT large](https://arxiv.org/pdf/1810.04805.pdf) | PyTorch | Training | [FP32 BFloat16 BFloat32](/models_v2/pytorch/bert_large/training/cpu/README.md) | [preprocessed text dataset](https://drive.google.com/drive/folders/1cywmDnAsrP5-2vsr8GDc6QUc7VWe-M3v) |
7474
| [DistilBERT base](https://arxiv.org/abs/1910.01108) | PyTorch | Inference | [FP32 BF32 BF16Int8-FP32 Int8-BFloat16 BFloat32](/models_v2/pytorch/distilbert/inference/cpu/README.md) | [ DistilBERT Base SQuAD1.1](https://huggingface.co/distilbert-base-uncased-distilled-squad) |
@@ -86,7 +86,7 @@ For best performance on Intel® Data Center GPU Flex and Max Series, please chec
8686

8787
| Model | Framework | Mode | Model Documentation | Benchmark/Test Dataset |
8888
| --------------------------------------------------------------- | ---------- | ----------| ------------------- | ---------------------- |
89-
| [BERT](https://arxiv.org/pdf/1810.04805.pdf) | TensorFlow | Inference | [FP32](/benchmarks/language_translation/tensorflow/bert/inference/README.md) | [MRPC](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#classification-training-with-bert) |
89+
| [BERT](https://arxiv.org/pdf/1810.04805.pdf) | TensorFlow | Inference | [FP32](/models_v2/tensorflow/bert/inference/cpu/README.md) | [MRPC](https://github.com/IntelAI/models/tree/master/datasets/bert_data/README.md#classification-training-with-bert) |
9090

9191
### Object Detection
9292

@@ -102,7 +102,7 @@ For best performance on Intel® Data Center GPU Flex and Max Series, please chec
102102

103103
| Model | Framework | Mode | Model Documentation | Benchmark/Test Dataset |
104104
| ------------------------------------------------------ | ---------- | ----------| ------------------- | ---------------------- |
105-
| [Wide & Deep](https://arxiv.org/pdf/1606.07792.pdf) | TensorFlow | Inference | [FP32](/benchmarks/recommendation/tensorflow/wide_deep/inference/README.md) | [Census Income dataset](https://github.com/IntelAI/models/tree/master/benchmarks/recommendation/tensorflow/wide_deep/inference/fp32#dataset) |
105+
| [Wide & Deep](https://arxiv.org/pdf/1606.07792.pdf) | TensorFlow | Inference | [FP32](/models_v2/tensorflow/wide_deep/inference/cpu/README.md) | [Census Income dataset](https://github.com/IntelAI/models/tree/master/benchmarks/recommendation/tensorflow/wide_deep/inference/fp32#dataset) |
106106
| [DLRM](https://arxiv.org/pdf/1906.00091.pdf) | PyTorch | Inference | [FP32 Int8 BFloat16 BFloat32](/models_v2/pytorch/dlrm/inference/cpu/README.md) | [Criteo Terabyte](/models_v2/pytorch/dlrm/inference/cpu/README.md#datasets) |
107107
| [DLRM](https://arxiv.org/pdf/1906.00091.pdf) | PyTorch | Training | [FP32 BFloat16 BFloat32](/models_v2/pytorch/dlrm/training/cpu/README.md) | [Criteo Terabyte](/models_v2/pytorch/dlrm/training/cpu/README.md#datasets) |
108108
| [DLRM v2](https://arxiv.org/pdf/1906.00091.pdf) | PyTorch | Inference | [FP32 FP16 BFloat16 BFloat32 Int8](/models_v2/pytorch/torchrec_dlrm/inference/cpu/README.md) | [Criteo 1TB Click Logs dataset](/models_v2/pytorch/torchrec_dlrm/inference/cpu#datasets) |
@@ -111,7 +111,7 @@ For best performance on Intel® Data Center GPU Flex and Max Series, please chec
111111

112112
| Model | Framework | Mode | Model Documentation | Benchmark/Test Dataset |
113113
| ----------------------------------------------- | ---------- | ----------| ------------------- | ---------------------- |
114-
| [Stable Diffusion](https://keras.io/guides/keras_cv/generate_images_with_stable_diffusion/) | TensorFlow | Inference | [FP32 BFloat16 FP16](/benchmarks/diffusion/tensorflow/stable_diffusion/inference/README.md) | [COCO 2017 validation dataset](https://github.com/IntelAI/models/tree/master/datasets/coco#download-and-preprocess-the-coco-validation-images)
114+
| [Stable Diffusion](https://keras.io/guides/keras_cv/generate_images_with_stable_diffusion/) | TensorFlow | Inference | [FP32 BFloat16 FP16](/models_v2/tensorflow/stable_diffusion/inference/cpu/README.md) | [COCO 2017 validation dataset](https://github.com/IntelAI/models/tree/master/datasets/coco#download-and-preprocess-the-coco-validation-images)
115115
| [Stable Diffusion](https://huggingface.co/stabilityai/stable-diffusion-2-1) | PyTorch | Inference | [FP32 BFloat16 FP16 BFloat32 Int8-FP32 Int8-BFloat16](/models_v2/pytorch/stable_diffusion/inference/cpu/README.md) | [COCO 2017 validation dataset](https://github.com/IntelAI/models/tree/master/datasets/coco#download-and-preprocess-the-coco-validation-images)
116116
| [Stable Diffusion](https://huggingface.co/stabilityai/stable-diffusion-2-1) | PyTorch | Training | [FP32 BFloat16 FP16 BFloat32](/models_v2/pytorch/stable_diffusion/training/cpu/README.md) | [cat images](https://huggingface.co/datasets/diffusers/cat_toy_example)
117117
| [Latent Consistency Models(LCM)](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) | PyTorch | Inference | [FP32 BFloat16 FP16 BFloat32 Int8-FP32 Int8-BFloat16](/models_v2/pytorch/LCM/inference/cpu/README.md) | [COCO 2017 validation dataset](https://github.com/IntelAI/models/tree/master/datasets/coco#download-and-preprocess-the-coco-validation-images)
@@ -120,7 +120,7 @@ For best performance on Intel® Data Center GPU Flex and Max Series, please chec
120120

121121
| Model | Framework | Mode | Model Documentation | Benchmark/Test Dataset |
122122
| ----------------------------------------------- | ---------- | ----------| ------------------- | ---------------------- |
123-
| [GraphSAGE](https://arxiv.org/pdf/1706.02216.pdf) | TensorFlow | Inference | [FP32 BFloat16 FP16 Int8 BFloat32](/benchmarks/graph_networks/tensorflow/graphsage/inference/README.md) | [Protein Protein Interaction](http://snap.stanford.edu/graphsage) |
123+
| [GraphSAGE](https://arxiv.org/pdf/1706.02216.pdf) | TensorFlow | Inference | [FP32 BFloat16 FP16 Int8 BFloat32](/models_v2/tensorflow/graphsage/inference/cpu/README.md) | [Protein Protein Interaction](http://snap.stanford.edu/graphsage) |
124124

125125
*Means the model belongs to [MLPerf](https://mlperf.org/) models and will be supported long-term.
126126

Diff for: ‎benchmarks/diffusion/tensorflow/stable_diffusion/inference/requirements.txt

-5
This file was deleted.

Diff for: ‎benchmarks/image_segmentation/tensorflow/3d_unet/README.md

-4
This file was deleted.

Diff for: ‎benchmarks/image_segmentation/tensorflow/3d_unet/inference/fp32/README.md

-146
This file was deleted.

0 commit comments

Comments
 (0)