add tf db_resnet benchmarks

mindee · Feb 27, 2024 · 33fb0d7 · 33fb0d7
1 parent 745f944
commit 33fb0d7
Showing 1 changed file with 8 additions and 8 deletions.
diff --git a/docs/source/using_doctr/using_models.rst b/docs/source/using_doctr/using_models.rst
@@ -36,7 +36,7 @@ For a comprehensive comparison, we have compiled a detailed benchmark on publicl
 +================+=================================+=================+==============+============+===============+============+===============+====================+
 | **Backend**    | **Architecture**                | **Input shape** | **# params** | **Recall** | **Precision** | **Recall** | **Precision** | **sec/it (B: 1)**  |
 +----------------+---------------------------------+-----------------+--------------+------------+---------------+------------+---------------+--------------------+
-| TensorFlow     | db_resnet50                     | (1024, 1024, 3) | 25.2 M       | 81.22      | 86.66         | 92.46      | 89.62         | 1.2                |
+| TensorFlow     | db_resnet50                     | (1024, 1024, 3) | 25.2 M       | 84.39      | 85.86         | 93.70      | 83.24         | 1.2                |
 +----------------+---------------------------------+-----------------+--------------+------------+---------------+------------+---------------+--------------------+
 | TensorFlow     | db_mobilenet_v3_large           | (1024, 1024, 3) | 4.2 M        | 78.27      | 82.77         | 80.99      | 66.57         | 0.5                |
 +----------------+---------------------------------+-----------------+--------------+------------+---------------+------------+---------------+--------------------+
@@ -205,19 +205,19 @@ For a comprehensive comparison, we have compiled a detailed benchmark on publicl
 +================+==========================================================+============================+============+===============+
 | **Backend**    | **Architecture**                                         | **Recall** | **Precision** | **Recall** | **Precision** |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
-| TensorFlow     | db_resnet50 + crnn_vgg16_bn                              | 70.82      | 75.56         | 83.97      | 81.40         |
+| TensorFlow     | db_resnet50 + crnn_vgg16_bn                              | 73.45      | 74.73         | 85.79      | 76.21         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
-| TensorFlow     | db_resnet50 + crnn_mobilenet_v3_small                    | 69.63      | 74.29         | 81.08      | 78.59         |
+| TensorFlow     | db_resnet50 + crnn_mobilenet_v3_small                    | 72.66      | 73.93         | 83.43      | 74.11         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
-| TensorFlow     | db_resnet50 + crnn_mobilenet_v3_large                    | 70.01      | 74.70         | 83.28      | 80.73         |
+| TensorFlow     | db_resnet50 + crnn_mobilenet_v3_large                    | 72.86      | 74.13         | 85.16      | 75.65         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
-| TensorFlow     | db_resnet50 + master                                     | 68.75      | 73.76         | 78.56      | 76.24         |
+| TensorFlow     | db_resnet50 + master                                     | 72.73      | 74.00         | 84.13      | 75.05         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
-| TensorFlow     | db_resnet50 + vitstr_small                               | 64.58      | 68.91         | 74.66      | 72.37         |
+| TensorFlow     | db_resnet50 + vitstr_small                               | 68.57      | 69.77         | 78.24      | 69.51         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
-| TensorFlow     | db_resnet50 + vitstr_base                                | 66.89      | 71.37         | 79.11      | 76.68         |
+| TensorFlow     | db_resnet50 + vitstr_base                                | 70.96      | 72.20         | 82.10      | 72.94         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
-| TensorFlow     | db_resnet50 + parseq                                     | 65.77      | 70.18         | 71.57      | 69.37         |
+| TensorFlow     | db_resnet50 + parseq                                     | 68.85      | 70.05         | 72.38      | 64.30         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+
 | PyTorch        | db_resnet50 + crnn_vgg16_bn                              | 72.43      | 75.13         | 85.05      | 79.33         |
 +----------------+----------------------------------------------------------+------------+---------------+------------+---------------+