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

Jump to bottom

[TFLite Export] Adds TFLite support for LayoutLMv3 #1372

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

[TFLite Export] Adds TFLite support for LayoutLMv3 #1372

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
43fbefb
Added TFLite Export for LayoutLMv3
salmanmaq Sep 8, 2023
a27359b
Merge branch 'main' into LayoutLMv3-TFLite-conversion-support
salmanmaq May 20, 2024
aa00dd6
Merge branch 'main' into LayoutLMv3-TFLite-conversion-support
salmanmaq Jun 3, 2024
b24bda2
Merge branch 'main' into LayoutLMv3-TFLite-conversion-support
salmanmaq Jun 24, 2024
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: 1 addition & 0 deletions optimum/exporters/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -700,6 +700,7 @@ class TasksManager:
"text-classification",
"token-classification",
onnx="LayoutLMv3OnnxConfig",
tflite="LayoutLMv3TFLiteConfig",
),
"lilt": supported_tasks_mapping(
"feature-extraction",
Expand Down
11 changes: 10 additions & 1 deletion optimum/exporters/tflite/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
configurations.
"""

from ...utils import DummyTextInputGenerator, DummyVisionInputGenerator, logging
from ...utils import DummyBboxInputGenerator, DummyTextInputGenerator, DummyVisionInputGenerator, logging
from .base import TFLiteConfig


Expand All @@ -40,3 +40,12 @@ class VisionTFLiteConfig(TFLiteConfig):

DUMMY_INPUT_GENERATOR_CLASSES = (DummyVisionInputGenerator,)
MANDATORY_AXES = ("batch_size", "num_channels", "width", "height")


class TextAndVisionTFLiteConfig(TFLiteConfig):
"""
Handles multi-modal text and vision architectures.
"""

DUMMY_INPUT_GENERATOR_CLASSES = (DummyTextInputGenerator, DummyVisionInputGenerator, DummyBboxInputGenerator)
MANDATORY_AXES = ("batch_size", "sequence_length", "num_channels", "width", "height")
16 changes: 14 additions & 2 deletions optimum/exporters/tflite/model_configs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,9 @@

from typing import List

from ...utils.normalized_config import NormalizedConfigManager
from ...utils.normalized_config import NormalizedConfigManager, NormalizedTextConfig
from .base import QuantizationApproach
from .config import TextEncoderTFliteConfig, VisionTFLiteConfig
from .config import TextAndVisionTFLiteConfig, TextEncoderTFliteConfig, VisionTFLiteConfig


class BertTFLiteConfig(TextEncoderTFliteConfig):
Expand Down Expand Up @@ -124,3 +124,15 @@ class ResNetTFLiteConfig(VisionTFLiteConfig):
@property
def inputs(self) -> List[str]:
return ["pixel_values"]


class LayoutLMv3TFLiteConfig(TextAndVisionTFLiteConfig):
SUPPORTED_QUANTIZATION_APPROACHES = (QuantizationApproach.INT8_DYNAMIC, QuantizationApproach.FP16)

NORMALIZED_CONFIG_CLASS = NormalizedTextConfig.with_args(
allow_new=True, MAX_2D_POSITION_EMBEDDINGS="max_2d_position_embeddings", image_size="input_size"
)

@property
def inputs(self) -> List[str]:
return ["input_ids", "attention_mask", "bbox", "pixel_values"]
Loading