| .. |
|
anomaly_detection
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
base
|
5f62d1a877
[Feat] Support multi-device inference and OCR batch inference (#3923)
|
há 6 meses atrás |
|
common
|
2fa8ad93b0
Add docbee2 (#3973)
|
há 6 meses atrás |
|
doc_vlm
|
2fa8ad93b0
Add docbee2 (#3973)
|
há 6 meses atrás |
|
face_feature
|
bc54f1bb90
[Infra] Prune and sort imports (#3694)
|
há 7 meses atrás |
|
formula_recognition
|
c7e439b896
Replace pymupdf with pdfium (#3947)
|
há 6 meses atrás |
|
image_classification
|
bc54f1bb90
[Infra] Prune and sort imports (#3694)
|
há 7 meses atrás |
|
image_feature
|
bc54f1bb90
[Infra] Prune and sort imports (#3694)
|
há 7 meses atrás |
|
image_multilabel_classification
|
bc54f1bb90
[Infra] Prune and sort imports (#3694)
|
há 7 meses atrás |
|
image_unwarping
|
bc54f1bb90
[Infra] Prune and sort imports (#3694)
|
há 7 meses atrás |
|
instance_segmentation
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
keypoint_detection
|
a589bbbe84
bugfix: kpt model support to pass dict as input
|
há 6 meses atrás |
|
m_3d_bev_detection
|
944b6d6a49
Allow import paddle (#3788)
|
há 7 meses atrás |
|
multilingual_speech_recognition
|
ad8719438a
add whisper and docbee models to benchmark (#3819)
|
há 7 meses atrás |
|
object_detection
|
3f070231aa
add layout and block model (#3967)
|
há 6 meses atrás |
|
open_vocabulary_detection
|
944b6d6a49
Allow import paddle (#3788)
|
há 7 meses atrás |
|
open_vocabulary_segmentation
|
944b6d6a49
Allow import paddle (#3788)
|
há 7 meses atrás |
|
semantic_segmentation
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
table_structure_recognition
|
9a2eeeaed3
support sort region
|
há 6 meses atrás |
|
text_detection
|
26957be66b
support 'max_side_limit' and change 'unclip_ratio' for OCR det model (#3979)
|
há 6 meses atrás |
|
text_recognition
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
ts_anomaly_detection
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
ts_classification
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
ts_forecasting
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
video_classification
|
f4a679ff9f
[Feat] Support lazy imports (#3764)
|
há 7 meses atrás |
|
video_detection
|
944b6d6a49
Allow import paddle (#3788)
|
há 7 meses atrás |
|
__init__.py
|
84b0edace4
bugfix: infer with official model
|
há 7 meses atrás |
学卿
26957be66b
support 'max_side_limit' and change 'unclip_ratio' for OCR det model (#3979)