scaleflex
/

clip-vit-base-patch32-openvino

Model card Files Files and versions Community

s-emanuilov commited on Oct 25, 2023

Commit

65c75be

·

1 Parent(s): 4e2644a

Update README.md

readme.md updates

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -12,16 +12,16 @@ The CLIP model was developed by researchers at OpenAI to learn about what contri
 ## Model type
 The model uses a ViT-B/32 Transformer architecture as an image encoder and uses a masked self-attention Transformer as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss.
-## OpenVINO optimization
 To increase the efficiency of the model during inference, we utilized the OpenVINO™ toolkit for optimization. The table below showcases the inference time improvements achieved with OpenVINO™ compared to the original PyTorch implementation:
-| Metric             |   PyTorch Inference Time (seconds) |   OpenVINO Inference Time (seconds) |   Similarity |
-|:-------------------|-----------------------------------:|------------------------------------:|-------------:|
-| Mean               |                           0.518564 |                           0.461107  |            1 |
-| Standard Deviation |                           0.109119 |                           0.0917191 |            0 |
-| Min                |                           0.390102 |                           0.360006  |            1 |
-| Max                |                           0.699677 |                           0.620042  |            1 |
 The results indicate that the OpenVINO™ optimization provides a consistent improvement in inference time while maintaining the same level of accuracy (as indicated by the similarity score).

 ## Model type
 The model uses a ViT-B/32 Transformer architecture as an image encoder and uses a masked self-attention Transformer as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss.
+## OpenVINO™ optimization
 To increase the efficiency of the model during inference, we utilized the OpenVINO™ toolkit for optimization. The table below showcases the inference time improvements achieved with OpenVINO™ compared to the original PyTorch implementation:
+| Metric             |   PyTorch Inference Time (sec) |   OpenVINO™ Inference Time (sec) |   Similarity |
+|:-------------------|-------------------------------:|---------------------------------:|-------------:|
+| mean               |                           0.52 |                            0.46  |            1 |
+| std                |                           0.11 |                            0.09  |            0 |
+| min                |                           0.39 |                            0.36  |            1 |
+| max                |                           0.70 |                            0.62  |            1 |
 The results indicate that the OpenVINO™ optimization provides a consistent improvement in inference time while maintaining the same level of accuracy (as indicated by the similarity score).