ai-models/PaddleOCR-VL
2
0
Fork 0
mirror of https://www.modelscope.cn/PaddlePaddle/PaddleOCR-VL.git synced 2026-04-02 13:32:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Upload to PaddlePaddle/PaddleOCR-VL on ModelScope hub

Browse Source
This commit is contained in:
TingquanGao
2025-10-16 10:41:48 +00:00
parent cf9c19bef2
commit c320f18247
44 changed files with 13893 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

176
PP-DocLayoutV2/config.json Normal file
View File

@ -0,0 +1,176 @@
{
"mode": "paddle",
"draw_threshold": 0.5,
"metric": "COCO",
"use_dynamic_shape": false,
"Global": {
"model_name": "PP-DocLayoutV2"
},
"arch": "DETR",
"min_subgraph_size": 3,
"Preprocess": [
{
"interp": 2,
"keep_ratio": false,
"target_size": [
800,
800
],
"type": "Resize"
},
{
"mean": [
0.0,
0.0,
0.0
],
"norm_type": "none",
"std": [
1.0,
1.0,
1.0
],
"type": "NormalizeImage"
},
{
"type": "Permute"
}
],
"label_list": [
"abstract",
"algorithm",
"aside_text",
"chart",
"content",
"display_formula",
"doc_title",
"figure_title",
"footer",
"footer_image",
"footnote",
"formula_number",
"header",
"header_image",
"image",
"inline_formula",
"number",
"paragraph_title",
"reference",
"reference_content",
"seal",
"table",
"text",
"vertical_text",
"vision_footnote"
],
"Hpi": {
"backend_configs": {
"paddle_infer": {
"trt_dynamic_shapes": {
"image": [
[
1,
3,
800,
800
],
[
1,
3,
800,
800
],
[
8,
3,
800,
800
]
],
"scale_factor": [
[
1,
2
],
[
1,
2
],
[
8,
2
]
]
},
"trt_dynamic_shape_input_data": {
"scale_factor": [
[
2,
2
],
[
1,
1
],
[
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67,
0.67
]
]
}
},
"tensorrt": {
"dynamic_shapes": {
"image": [
[
1,
3,
800,
800
],
[
1,
3,
800,
800
],
[
8,
3,
800,
800
]
],
"scale_factor": [
[
1,
2
],
[
1,
2
],
[
8,
2
]
]
}
}
}
}
}

3
PP-DocLayoutV2/inference.pdiparams Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:45404a84c9fdf91d7bbc94bd47ac4c03649bda84167de04c62bff4726657869a
size 212170944

3
PP-DocLayoutV2/inference.pdmodel Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fddd4b4359b95e6f1dd86c86f05e9516517bead9089287681838cdcbf003563b
size 1515181

100
PP-DocLayoutV2/inference.yml Normal file
View File

@ -0,0 +1,100 @@
mode: paddle
draw_threshold: 0.5
metric: COCO
use_dynamic_shape: false
Global:
model_name: PP-DocLayoutV2
arch: DETR
min_subgraph_size: 3
Preprocess:
- interp: 2
keep_ratio: false
target_size:
- 800
- 800
type: Resize
- mean:
- 0.0
- 0.0
- 0.0
norm_type: none
std:
- 1.0
- 1.0
- 1.0
type: NormalizeImage
- type: Permute
label_list:
- abstract
- algorithm
- aside_text
- chart
- content
- display_formula
- doc_title
- figure_title
- footer
- footer_image
- footnote
- formula_number
- header
- header_image
- image
- inline_formula
- number
- paragraph_title
- reference
- reference_content
- seal
- table
- text
- vertical_text
- vision_footnote
Hpi:
backend_configs:
paddle_infer:
trt_dynamic_shapes: &id001
image:
- - 1
- 3
- 800
- 800
- - 1
- 3
- 800
- 800
- - 8
- 3
- 800
- 800
scale_factor:
- - 1
- 2
- - 1
- 2
- - 8
- 2
trt_dynamic_shape_input_data:
scale_factor:
- - 2
- 2
- - 1
- 1
- - 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
- 0.67
tensorrt:
dynamic_shapes: *id001