Updated efficientnet-b0-pytorch model (#3336)

Author: Anna Grebneva

models/public/efficientnet-b0-pytorch/README.md

@@ -25,8 +25,8 @@ The model output for `efficientnet-b0-pytorch` is the typical object classifier
 
 | Metric | Original model | Converted model |
 | ------ | -------------- | --------------- |
-| Top 1  | 76.91%          | 76.91%         |
-| Top 5  | 93.21%          | 93.21%         |
+| Top 1  | 77.70%          | 77.70%         |
+| Top 5  | 93.52%          | 93.52%         |
 
 ## Input
 

models/public/efficientnet-b0-pytorch/accuracy-check.yml

@@ -33,11 +33,11 @@ models:
           - name: accuracy@top1
             type: accuracy
             top_k: 1
-            reference: 0.7691
+            reference: 0.777
           - name: accuracy@top5
             type: accuracy
             top_k: 5
-            reference: 0.9321
+            reference: 0.9352
 
   - name: efficientnet-b0-pytorch
 
@@ -65,8 +65,8 @@ models:
           - name: accuracy@top1
             type: accuracy
             top_k: 1
-            reference: 0.7691
+            reference: 0.777
           - name: accuracy@top5
             type: accuracy
             top_k: 5
-            reference: 0.9321
+            reference: 0.9352

models/public/efficientnet-b0-pytorch/model.yml

@@ -50,10 +50,10 @@ files:
     original_source: https://github.com/rwightman/gen-efficientnet-pytorch/raw/a36e2b2cd1bd122a508a6fffeaa7606890f8c882/gen_efficientnet/__init__.py
     source: https://storage.openvinotoolkit.org/repositories/open_model_zoo/public/2022.1/efficientnet-b0-pytorch/__init__.py
   - name: efficientnet-b0.pth
-    size: 21376958
-    checksum: f44c3ff7ceeeda4ccf95a6720483cf2bee89f2db59d47e8349d2a7d46024e006b76e92105b6723060b898505312e70ff
-    original_source: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/efficientnet_b0-d6904d92.pth
-    source: https://storage.openvinotoolkit.org/repositories/open_model_zoo/public/2022.1/efficientnet-b0-pytorch/efficientnet_b0-d6904d92.pth
+    size: 21376743
+    checksum: f6926743bf2213489f95c3b4bc6edc358ed9623780306e329ac8184ae36114237d98aa772761c180608316731db8e586
+    original_source: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/efficientnet_b0_ra-3dd342df.pth
+    source: https://storage.openvinotoolkit.org/repositories/open_model_zoo/public/2022.2/efficientnet-b0-pytorch/efficientnet_b0_ra-3dd342df.pth
 conversion_to_onnx_args:
   - --model-path=$dl_dir
   - --model-name=efficientnet_b0

models/public/index.md

@@ -332,7 +332,7 @@ You can download models and convert them into OpenVINO™ IR format (\*.xml + \*
 | CaffeNet                    | Caffe\*                            | [caffenet](./caffenet/README.md)  | 56.714%/79.916% | 1.5 | 60.965 |
 | DenseNet 121                | Caffe\*<br>TensorFlow\*| [densenet-121](./densenet-121/README.md)<br>[densenet-121-tf](./densenet-121-tf/README.md)| 74.42%/92.136%<br>74.46%/92.13%| 5.723~5.7287 | 7.971 |
 | DLA 34                      | PyTorch\*                          | [dla-34](./dla-34/README.md) | 74.64%/92.06% | 6.1368 | 15.7344 |
-| EfficientNet B0             | TensorFlow\*<br>PyTorch\*          | [efficientnet-b0](./efficientnet-b0/README.md)<br>[efficientnet-b0-pytorch](./efficientnet-b0-pytorch/README.md) | 75.70%/92.76%<br>76.91%/93.21% | 0.819 | 5.268 |
+| EfficientNet B0             | TensorFlow\*<br>PyTorch\*          | [efficientnet-b0](./efficientnet-b0/README.md)<br>[efficientnet-b0-pytorch](./efficientnet-b0-pytorch/README.md) | 75.70%/92.76%<br>77.70%/93.52% | 0.819 | 5.268 |
 | EfficientNet V2 B0          | PyTorch\*                          | [efficientnet-v2-b0](./efficientnet-v2-b0/README.md) | 78.36%/94.02% | 1.4641 | 7.1094 |
 | EfficientNet V2 Small       | PyTorch\*                          | [efficientnet-v2-s](./efficientnet-v2-s/README.md) | 84.29%/97.26% | 16.9406  | 21.3816  |
 | HBONet 1.0                  | PyTorch\*                          | [hbonet-1.0](./hbonet-1.0/README.md)  | 73.1%/91.0% | 0.6208 | 4.5443 |