mirrors
/
mmdeploy
mirror of https://github.com/open-mmlab/mmdeploy.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Add new configs for ocr (#295) 

* save configs

* add to benchmark

* add datasets to benchmark

* lock mmcor version to 0.3.0
pull/1/head
AllentDan 2021-12-15 19:51:38 +08:00 committed by GitHub
parent 43256977fa
commit 3eabeae071
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 513 additions and 468 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
configs/mmocr/text-detection/text-detection_openvino_dynamic.py 100644
View File

@ -0,0 +1,3 @@
_base_ = ['./text-detection_dynamic.py', '../../_base_/backends/openvino.py']
onnx_config = dict(strip_doc_string=False)

3
configs/mmocr/text-detection/text-detection_openvino_static-640x640.py 100644
View File

@ -0,0 +1,3 @@
_base_ = ['./text-detection_static.py', '../../_base_/backends/openvino.py']
onnx_config = dict(input_shape=(640, 640), strip_doc_string=False)

5
configs/mmocr/text-recognition/text-recognition_pplnn_dynamic-1x32x32.py 100644
View File

@ -0,0 +1,5 @@
_base_ = ['./text-recognition_dynamic.py', '../../_base_/backends/pplnn.py']
onnx_config = dict(input_shape=None)
backend_config = dict(model_inputs=dict(opt_shape=[1, 1, 32, 32]))

964
docs/benchmark.md
View File

File diff suppressed because it is too large Load Diff

2
docs/codebases/mmocr.md
View File

@ -11,7 +11,7 @@ Please refer to [install.md](https://github.com/open-mmlab/mmocr/blob/main/docs/
| model | task | OnnxRuntime | TensorRT | NCNN | PPLNN | OpenVINO | model config file(example) |
|-------|:----------------:|:-----------:|:--------:|:----:|:---:|:--------:|---------------------------------------------------------------------------|
| DBNet | text-detection | Y | Y | Y | Y | Y | $PATH_TO_MMOCR/configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py |
| CRNN | text-recognition | Y | Y | Y | N | N | $PATH_TO_MMOCR/configs/textrecog/crnn/crnn_academic_dataset.py |
| CRNN | text-recognition | Y | Y | Y | Y | N | $PATH_TO_MMOCR/configs/textrecog/crnn/crnn_academic_dataset.py |
| SAR | text-recognition | Y | N | N | N | N | $PATH_TO_MMOCR/configs/textrecog/sar/sar_r31_parallel_decoder_academic.py |

2
docs/tutorials/how_to_convert_model.md
View File

@ -115,7 +115,7 @@ The table below lists the models that are guaranteed to be exportable to other b
| SRCNN | MMEditing | Y | Y | N | Y | N | $MMSEG_DIR/configs/restorers/srcnn/srcnn_x4k915_g1_1000k_div2k.py |
| ESRGAN | MMEditing | Y | Y | N | Y | N | $MMSEG_DIR/configs/restorers/esrgan/esrgan_psnr_x4c64b23g32_g1_1000k_div2k.py |
| DBNet | MMOCR | Y | Y | Y | Y | Y | $MMOCR_DIR/configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py |
| CRNN | MMOCR | Y | Y | Y | N | N | $MMOCR_DIR/configs/textrecog/crnn/crnn_academic_dataset.py |
| CRNN | MMOCR | Y | Y | Y | Y | N | $MMOCR_DIR/configs/textrecog/crnn/crnn_academic_dataset.py |
### Reminders

2
requirements/optional.txt
View File

@ -1,7 +1,7 @@
mmcls>=0.15.0
mmdet>=2.19.0
mmedit
mmocr>=0.3.0
mmocr==0.3.0
mmsegmentation
ncnn
onnxruntime>=1.8.0