Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: Benchmark of crnn_mobilenet_v3 small #523

Merged
merged 8 commits into from
Oct 4, 2021
Merged

feat: Benchmark of crnn_mobilenet_v3 small #523

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
69e267f
feat: add pytorch ckpts for crnn & mobilenet_v3_large
charlesmindee Sep 21, 2021
24c9254
Merge branch 'main' of github.com:mindee/doctr into main
charlesmindee Sep 22, 2021
4a3d879
Merge branch 'main' of github.com:mindee/doctr into main
charlesmindee Sep 22, 2021
3ad9cd3
Merge branch 'main' of github.com:mindee/doctr into main
charlesmindee Sep 30, 2021
ad5e1df
Merge branch 'main' of github.com:mindee/doctr into main
charlesmindee Sep 30, 2021
56b4b95
Merge branch 'main' of github.com:mindee/doctr into main
charlesmindee Oct 4, 2021
29a80d9
Merge branch 'main' of github.com:mindee/doctr into main
charlesmindee Oct 4, 2021
96e2442
feat: add crnn_mobilenet tf bench
charlesmindee Oct 4, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 23 additions & 19 deletions docs/source/using_models.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,8 @@ For a comprehensive comparison, we have compiled a detailed benchmark on publicl
* - crnn_mobilenet_v3_small
- (32, 128, 3)
- 2.1M
-
-
- 86.21
- 90.56
-
* - crnn_mobilenet_v3_large
- (32, 128, 3)
Expand Down Expand Up @@ -171,6 +171,8 @@ For a comprehensive comparison, we have compiled a detailed benchmark on publicl
+----------------------------------------+------------+---------------+---------+------------+---------------+---------+
| db_resnet50 + sar_resnet31 | 71.25 | 76.29 | 0.27 | 84.50 | **81.96** | 0.83 |
+----------------------------------------+------------+---------------+---------+------------+---------------+---------+
| db_resnet50 + crnn_mobilenet_v3_small | 69.85 | 74.80 | | 80.85 | 78.42 | 0.83 |
+----------------------------------------+------------+---------------+---------+------------+---------------+---------+
| db_mobilenet_v3_large + crnn_vgg16_bn | 67.73 | 71.73 | | 71.65 | 59.03 | |
+----------------------------------------+------------+---------------+---------+------------+---------------+---------+
| Gvision text detection | 59.50 | 62.50 | | 75.30 | 70.00 | |
Expand All @@ -190,23 +192,25 @@ FPS (Frames per second) is computed after a warmup phase of 100 tensors (where t
Since you may be looking for specific use cases, we also performed this benchmark on private datasets with various document types below. Unfortunately, we are not able to share those at the moment since they contain sensitive information.


+----------------------------------------------+----------------------------+----------------------------+----------------------------+----------------------------+
| | Receipts | Invoices | IDs | US Tax Forms |
+==============================================+============+===============+============+===============+============+===============+============+===============+
| **Architecture** | **Recall** | **Precision** | **Recall** | **Precision** | **Recall** | **Precision** | **Recall** | **Precision** |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_resnet50 + crnn_vgg16_bn (ours) | 78.70 | 81.12 | 65.80 | 70.70 | 50.25 | 51.78 | 79.08 | 92.83 |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_resnet50 + master (ours) | **79.00** | **81.42** | 65.57 | 69.86 | 51.34 | 52.90 | 78.86 | 92.57 |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_resnet50 + sar_resnet31 (ours) | 78.94 | 81.37 | 65.89 | **70.79** | **51.78** | **53.35** | 79.04 | 92.78 |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_mobilenet_v3_large + crnn_vgg16_bn (ours) | 78.36 | 74.93 | 63.04 | 68.41 | 39.36 | 41.75 | 72.14 | 89.97 |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| Gvision doc. text detection | 68.91 | 59.89 | 63.20 | 52.85 | 43.70 | 29.21 | 69.79 | 65.68 |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| AWS textract | 75.77 | 77.70 | **70.47** | 69.13 | 46.39 | 43.32 | **84.31** | **98.11** |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
+----------------------------------------------+----------------------------+----------------------------+----------------------------+----------------------------+----------------------------+----------------------------+
| | Receipts | Invoices | IDs | US Tax Forms | Resumes | Road Fines |
+==============================================+============+===============+============+===============+============+===============+============+===============+============+===============+============+===============+
| **Architecture** | **Recall** | **Precision** | **Recall** | **Precision** | **Recall** | **Precision** | **Recall** | **Precision** | **Recall** | **Precision** | **Recall** | **Precision** |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_resnet50 + crnn_vgg16_bn (ours) | 78.70 | 81.12 | 65.80 | 70.70 | 50.25 | 51.78 | 79.08 | 92.83 | | | | |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_resnet50 + master (ours) | **79.00** | **81.42** | 65.57 | 69.86 | 51.34 | 52.90 | 78.86 | 92.57 | | | | |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_resnet50 + sar_resnet31 (ours) | 78.94 | 81.37 | 65.89 | **70.79** | **51.78** | **53.35** | 79.04 | 92.78 | | | | |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_resnet50 + crnn_mobilenet_v3_small (ours) | 76.81 | 79.15 | 64.89 | 69.61 | 45.03 | 46.38 | 78.96 | 92.11 | 85.91 | 87.20 | 84.85 | 85.86 |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| db_mobilenet_v3_large + crnn_vgg16_bn (ours) | 78.36 | 74.93 | 63.04 | 68.41 | 39.36 | 41.75 | 72.14 | 89.97 | | | | |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| Gvision doc. text detection | 68.91 | 59.89 | 63.20 | 52.85 | 43.70 | 29.21 | 69.79 | 65.68 | | | | |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+
| AWS textract | 75.77 | 77.70 | **70.47** | 69.13 | 46.39 | 43.32 | **84.31** | **98.11** | | | | |
+----------------------------------------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+------------+---------------+


Two-stage approaches
Expand Down