[Docs ]change benchmarks to version 23.3 (openvinotoolkit#22353)

* change benchmarks to 23.3 * Update docs/articles_en/about_openvino/performance_benchmarks/performance_int8_vs_fp32.rst * Update docs/articles_en/about_openvino/performance_benchmarks/performance_int8_vs_fp32.rst --------- Co-authored-by: Sebastian Golebiewski <[email protected]>
DanLiu2Intel · Jan 23, 2024 · 0666d12 · 0666d12
1 parent f1ef5f2
commit 0666d12
Show file tree

Hide file tree

Showing 9 changed files with 675 additions and 507 deletions.
diff --git a/docs/articles_en/about_openvino/performance_benchmarks.rst b/docs/articles_en/about_openvino/performance_benchmarks.rst
@@ -15,7 +15,7 @@ Performance Benchmarks
 
    openvino_docs_performance_benchmarks_faq
    OpenVINO Accuracy <openvino_docs_performance_int8_vs_fp32>
-   Performance Data Spreadsheet (download xlsx) <https://docs.openvino.ai/2023.2/_static/benchmarks_files/OV-2023.2-Performance-Data.xlsx> 
+   Performance Data Spreadsheet (download xlsx) <https://docs.openvino.ai/2023.2/_static/benchmarks_files/OV-2023.3-Performance-Data.xlsx> 
    openvino_docs_MO_DG_Getting_Performance_Numbers
 
 
@@ -102,14 +102,14 @@ For a listing of all platforms and configurations used for testing, refer to the
 
    .. grid-item::
 
-      .. button-link:: _static/benchmarks_files/OV-2023.2-platform_list.pdf
+      .. button-link:: _static/benchmarks_files/OV-2023.3-platform_list.pdf
          :color: primary
          :outline:
          :expand:
 
          :material-regular:`download;1.5em` Click for Hardware Platforms [PDF]
 
-      .. button-link:: _static/benchmarks_files/OV-2023.2-system-info-detailed.xlsx
+      .. button-link:: _static/benchmarks_files/OV-2023.3-system-info-detailed.xlsx
          :color: primary
          :outline:
          :expand:

diff --git a/...rticles_en/about_openvino/performance_benchmarks/performance_benchmarks_faq.rst b/...rticles_en/about_openvino/performance_benchmarks/performance_benchmarks_faq.rst
@@ -57,6 +57,10 @@ Performance Information F.A.Q.
         - Meta AI
         - Auto regressive language
         - 4096
+      * - `Mistral-7b <https://huggingface.co/mistralai/Mistral-7B-v0.1>`__
+        - Mistral AI
+        - Auto regressive language
+        - 4096
       * - `Stable-Diffusion-V2-1 <https://huggingface.co/stabilityai/stable-diffusion-2-1>`__
         - Hugginface
         - Latent Diffusion Model
@@ -69,18 +73,14 @@ Performance Information F.A.Q.
         - BERT-large
         - question / answer
         - 384
-      * - `deeplabv3 <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/deeplabv3>`__
-        -  DeepLab v3 Tf
-        - semantic segmentation
-        - 513x513
       * - `efficientdet-d0 <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/efficientdet-d0-tf>`__
         - Efficientdet
         - classification
         - 512x512
-      * - `faster_rcnn_resnet50_coco <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/faster_rcnn_resnet50_coco>`__
-        - Faster RCNN TF
-        - object detection
-        - 600x1024
+      * - `mask_rcnn_resnet50_atrous_coco <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/mask_rcnn_resnet50_atrous_coco>`__
+        - Mask R-CNN ResNet 50 Atrous
+        - object instance segmentation
+        - 800x1365
       * - `mobilenet-v2 <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/mobilenet-v2-pytorch>`__
         - Mobilenet V2 PyTorch
         - classification
@@ -101,10 +101,6 @@ Performance Information F.A.Q.
         - U-Net
         - semantic segmentation
         - 368x480     
-      * - `yolo-v3 <https://https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/yolo-v3-tf>`__
-        - YOLO v3 
-        - object detection
-        - 416x416      
       * - `yolo-v3-tiny <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/yolo-v3-tiny-tf>`__
         - YOLO v3 Tiny
         - object detection
@@ -164,4 +160,3 @@ Performance Information F.A.Q.
    for autonomous vehicles, where a quick response to the result of the
    inference is required.
 
-