q792602257/agentic-mobile-control
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
178 Commits 1 Branch 0 Tags
17a709c92fdd70ef2a7954eccf9d84afcc0abfe3
Commit Graph
3 Commits
Author SHA1 Message Date
q792602257 17a709c92f fix(perception): disable PaddleOCR doc-unwarping for screenshots
Tests / Test tests.test_device_config.test_device_config_store_settings_get_set_and_defaults failed
Details 
PaddleOCR's OCR.yaml pipeline defaults to use_doc_orientation_classify
and use_doc_unwarping enabled, which are meant for photographed paper
documents. Applied to a flat, upright device screenshot, UVDoc
geometrically warps the image before detection, and returns box
coordinates in that warped space with no inverse mapping back to the
original image.

Verified on a real screenshot: with unwarping on, the same detected
element ("新项目") shifts from y=158 to y=71 versus the original image,
and 2 boxes near the top edge (status bar time/battery) are dropped
entirely. Disabling both flags by default (still overridable via
explicit kwargs) makes detected boxes match the original screenshot.
 2026-07-15 16:51:36 +08:00
q792602257 6e511111c4 fix(perception): harden PaddleOCR result handling
Tests / Test passed: 793
Details
2026-07-14 20:07:49 +08:00
q792602257 5658735bca feat: checkpoint device agent runtime milestones 2026-07-06 17:24:03 +08:00