 myhloli
|
553f250fc7
refactor(magic_pdf): optimize code and improve logging
|
7 月之前 |
|
myhloli
|
243bc58cc6
refactor(magic_pdf): remove unused imports and update dependencies
|
7 月之前 |
|
myhloli
|
a330651d64
feat(ocr): implement separate detection and recognition processes
|
7 月之前 |
 icecraft
|
4fbc368988
feat: remove old inference code
|
7 月之前 |
|
icecraft
|
bbba2a120c
feat: batch inference with ocr and lang flag
|
7 月之前 |
|
icecraft
|
adbf492111
fix: support auto method and auto lang
|
7 月之前 |
|
myhloli
|
2f40fa7d3c
perf(inference): adjust batch ratio for GPU memory sizes
|
8 月之前 |
|
myhloli
|
74e954dace
perf(inference): adjust batch ratio thresholds for GPU memory sizes
|
8 月之前 |
|
myhloli
|
cf4ea78dac
refactor: remove torchtext deprecation warning handling
|
8 月之前 |
|
myhloli
|
af27c0cc81
refactor(magic_pdf): support mps device and optimize image processing
|
8 月之前 |
|
icecraft
|
e9c2473913
style: remove unused code
|
8 月之前 |
|
icecraft
|
b50f742fd9
feat: add parallel evalution
|
8 月之前 |
|
icecraft
|
3a2f86a1b6
feat: add parallel evalution
|
8 月之前 |
|
myhloli
|
6116488d88
perf(inference): optimize batch processing for different GPU memory sizes
|
8 月之前 |
|
myhloli
|
0b05dff74f
perf(inference): adjust batch ratio for high GPU memory
|
8 月之前 |
|
myhloli
|
58b6ad8ca2
perf(inference): adjust batch ratio for GPU memory sizes
|
8 月之前 |
|
myhloli
|
0d3304d7c9
perf(inference): adjust batch ratio for GPU memory sizes
|
8 月之前 |
|
myhloli
|
6753df8dd3
perf(model): optimize batch analyze process
|
8 月之前 |
|
myhloli
|
90a27ecd26
fix(magic_pdf): correct negative indexing for `end_page_id`
|
8 月之前 |
|
Xiaomeng Zhao
|
886d253cf3
Merge pull request #1748 from nadahlberg/master
|
8 月之前 |
 Nathan Dahlberg
|
37f3e200da
fix doc_analyze first page only
|
8 月之前 |
|
myhloli
|
f5112e2157
fix(model): move environment variable settings to global scope
|
9 月之前 |
|
myhloli
|
4021abeb98
refactor(magic_pdf): improve code structure and memory safety
|
9 月之前 |
|
myhloli
|
7c76d3610f
refactor(model): integrate Ascend plugin for NPU support
|
9 月之前 |
|
myhloli
|
b1ac7afdaa
perf(model): optimize batch ratio for different GPU memory sizes
|
9 月之前 |
|
myhloli
|
29e7a9488f
perf(model): adjust batch ratio for different GPU memory sizes
|
9 月之前 |
|
myhloli
|
d1af456621
perf(model): adjust batch ratio for GPU memory range
|
9 月之前 |
|
myhloli
|
b6710b9988
fix(magic_pdf): correct batch ratio conditions for GPU memory
|
10 月之前 |
|
myhloli
|
55447c8b64
perf(magic_pdf): optimize batch processing for GPU
|
10 月之前 |
|
myhloli
|
037736fbaf
perf(magic_pdf): adjust batch ratio calculation for GPU memory
|
10 月之前 |
