Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix ray version #56

Merged
merged 1 commit into from
Jan 3, 2024
Merged

Fix ray version #56

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,6 @@ def main():
num_gpus=1 if settings.CUDA else 0,
storage=settings.RAY_CACHE_PATH,
_temp_dir=settings.RAY_CACHE_PATH,
dashboard_host=settings.RAY_DASHBOARD_HOST,
log_to_driver=settings.DEBUG
)

Expand Down
3 changes: 1 addition & 2 deletions marker/debug/data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,10 @@ def dump_equation_debug_data(doc, images, converted_spans):
assert len(converted_spans) == len(images)

data_lines = []
for idx, (image, converted_span) in enumerate(zip(images, converted_spans)):
for idx, (pil_image, converted_span) in enumerate(zip(images, converted_spans)):
if converted_span is None:
continue
# Image is a BytesIO object
pil_image = Image.open(image)
img_bytes = io.BytesIO()
pil_image.save(img_bytes, format="WEBP", lossless=True)
b64_image = base64.b64encode(img_bytes.getvalue()).decode("utf-8")
Expand Down
3 changes: 1 addition & 2 deletions marker/settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ def TORCH_DEVICE_MODEL(self) -> str:
TEXIFY_MODEL_MAX: int = 384 # Max inference length for texify
TEXIFY_TOKEN_BUFFER: int = 256 # Number of tokens to buffer above max for texify
TEXIFY_DPI: int = 96 # DPI to render images at
TEXIFY_BATCH_SIZE: int = 1 if TORCH_DEVICE_MODEL == "cpu" else 6 # Batch size for texify, don't batch on cpu
TEXIFY_BATCH_SIZE: int = 2 if TORCH_DEVICE_MODEL == "cpu" else 6 # Batch size for texify, lower on cpu due to float32
TEXIFY_MODEL_NAME: str = "vikp/texify"

# Layout model
Expand All @@ -102,7 +102,6 @@ def TORCH_DEVICE_MODEL(self) -> str:

# Ray
RAY_CACHE_PATH: Optional[str] = None # Where to save ray cache
RAY_DASHBOARD_HOST: str = "127.0.0.1"
RAY_CORES_PER_WORKER: int = 1 # How many cpu cores to allocate per worker

# Debug
Expand Down
57 changes: 28 additions & 29 deletions poetry.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

6 changes: 3 additions & 3 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,11 +27,11 @@ PyMuPDF = "^1.23.5"
pymupdf-fonts = "^1.0.5"
pydantic = "^2.4.2"
pydantic-settings = "^2.0.3"
transformers = "^4.34.1"
transformers = "^4.36.2"
numpy = "^1.26.1"
python-dotenv = "^1.0.0"
torch = "^2.1.1"
ray = "^2.7.1"
torch = "^2.1.2"
ray = "^2.9.0"
tqdm = "^4.66.1"
tabulate = "^0.9.0"
thefuzz = "^0.20.0"
Expand Down