ENOT-AutoDL
/

imagenet-benchmark

Image Classification

Inference Endpoints

Model card Files Files and versions Community

andreysher commited on Sep 18, 2023

Commit

36e5a58

·

1 Parent(s): 4d679c2

Update README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -17,25 +17,25 @@ Evaluation code is also based on Torchvision references.
 ## ResNet-50
-| Model                     |  Latency (MMACs)  |  Accuracy (%)   |
-| ------------------------- | :---------------: | :-------------: |
-| **ResNet-50 Torchvision** |     4144.854      |     76.144      |
-| **ResNet-50 ENOT (x2)**   | 2057.615 (x2.014) | 75.482 (-0.662) |
-| **ResNet-50 ENOT (x4)**   | 867.943 (x4.775)  | 73.576 (-2.568) |
 ## ViT-B/32
-| Model                    | Latency (MMACs)  |  Accuracy (%)   |
-| ------------------------ | :--------------: | :-------------: |
-| **ViT-B/32 Torchvision** |     4413.986     |     75.912      |
-| **ViT-B/32 ENOT**        | 492.232 (x8.967) | 73.718 (-2.194) |
 ## MobileNetV2
-| Model                       | Latency (MMACs)  |  Accuracy (%)  |
-| --------------------------- | :--------------: | :------------: |
-| **MobileNetV2 Torchvision** |     334.227      |     71.878     |
-| **MobileNetV2 ENOT**        | 156.800 (x2.131) | 69.898 (-1.98) |
 # Validation

 ## ResNet-50
+| Model                     | Latency (MMACs) | Accuracy (%)  |
+|---------------------------|:---------------:|:-------------:|
+| **ResNet-50 Torchvision** |     4144.85     |     76.14     |
+| **ResNet-50 ENOT (x2)**   | 2057.61 (x2.01) | 75.48 (-0.66) |
+| **ResNet-50 ENOT (x4)**   | 867.94 (x4.77)  | 73.58 (-2.57) |
 ## ViT-B/32
+| Model                    | Latency (MMACs) | Accuracy (%)  |
+|--------------------------|:---------------:|:-------------:|
+| **ViT-B/32 Torchvision** |     4413.99     |     75.91     |
+| **ViT-B/32 ENOT**        | 492.23 (x8.97)  | 73.72 (-2.19) |
 ## MobileNetV2
+| Model                       | Latency (MMACs) | Accuracy (%)  |
+|-----------------------------|:---------------:|:-------------:|
+| **MobileNetV2 Torchvision** |     334.23      |     71.88     |
+| **MobileNetV2 ENOT**        | 156.80 (x2.13)  | 69.90 (-1.98) |
 # Validation