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

Add ONNX export support for GIT #2132

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Add ONNX export support for GIT #2132

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e369e24
Add ONNX export support for GIT
marcindulak Dec 19, 2024
ea2321c
Use single GITOnnxConfig class
marcindulak Dec 20, 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 docs/source/exporters/onnx/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@ Supported architectures from [🤗 Transformers](https://huggingface.co/docs/tra
- ESM
- Falcon
- Flaubert
- GIT
- GPT-2
- GPT-BigCode
- GPT-J
Expand Down
1 change: 1 addition & 0 deletions optimum/exporters/onnx/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,6 +150,7 @@ class OnnxConfig(ExportConfig, ABC):
"fill-mask": OrderedDict({"logits": {0: "batch_size", 1: "sequence_length"}}),
"image-classification": OrderedDict({"logits": {0: "batch_size"}}),
"image-segmentation": OrderedDict({"logits": {0: "batch_size", 1: "num_labels", 2: "height", 3: "width"}}),
"image-text-to-text": OrderedDict({"logits": {0: "batch_size", 1: "sequence_length"}}),
"image-to-text": OrderedDict({"logits": {0: "batch_size", 1: "sequence_length"}}),
"image-to-image": OrderedDict(
{"reconstruction": {0: "batch_size", 1: "num_channels", 2: "height", 3: "width"}}
Expand Down
32 changes: 32 additions & 0 deletions optimum/exporters/onnx/model_configs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2621,3 +2621,35 @@ class EncoderDecoderOnnxConfig(EncoderDecoderBaseOnnxConfig):
NORMALIZED_CONFIG_CLASS = NormalizedEncoderDecoderConfig

DEFAULT_ONNX_OPSET = 14 # uses SDPA in Transformers, hence opset>=14.


class GITOnnxConfig(TextAndVisionOnnxConfig):
NORMALIZED_CONFIG_CLASS = NormalizedTextAndVisionConfig.with_args(vision_config="vision_config")
DUMMY_INPUT_GENERATOR_CLASSES_MAP = {
"feature-extraction": (DummyVisionInputGenerator,),
"image-text-to-text": (DummyTextInputGenerator, DummyVisionInputGenerator,),
"image-to-text": (DummyVisionInputGenerator,),
}

def _create_dummy_input_generator_classes(self, **kwargs) -> List["DummyInputGenerator"]:
dummy_inputs_generators = []
for dummy_input_generator in self.DUMMY_INPUT_GENERATOR_CLASSES_MAP[self.task]:
print(self.task, dummy_input_generator)
dummy_input_generator_instantiated = dummy_input_generator(
self.task, self._normalized_config, **kwargs
)
dummy_inputs_generators.append(dummy_input_generator_instantiated)

return dummy_inputs_generators

@property
def inputs(self) -> Dict[str, Dict[int, str]]:
if self.task == "image-text-to-text":
return {
"input_ids": {0: "text_batch_size", 1: "sequence_length"},
"pixel_values": {0: "image_batch_size", 1: "num_channels", 2: "height", 3: "width"},
}
else:
return {
"pixel_values": {0: "image_batch_size", 1: "num_channels", 2: "height", 3: "width"},
}
7 changes: 7 additions & 0 deletions optimum/exporters/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -215,6 +215,7 @@ class TasksManager:
"AutoModelForInstanceSegmentation",
"AutoModelForUniversalSegmentation",
),
"image-text-to-text": ("AutoModelForCausalLM", "AutoModel"),
"image-to-image": "AutoModelForImageToImage",
"image-to-text": ("AutoModelForVision2Seq", "AutoModel"),
"mask-generation": "AutoModel",
Expand Down Expand Up @@ -692,6 +693,12 @@ class TasksManager:
"text-classification",
onnx="GemmaOnnxConfig",
),
"git": supported_tasks_mapping(
"feature-extraction",
"image-text-to-text",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The issue
KeyError: "Unknown task: image-text-to-text. Possible values are: `audio-classification` for AutoModelForAudioClassification, `audio-frame-classification` for AutoModelForAudioFrameClassification, `audio-xvector` for AutoModelForAudioXVector, `automatic-speech-recognition` for ('AutoModelForSpeechSeq2Seq', 'AutoModelForCTC'), `depth-estimation` for AutoModelForDepthEstimation, `feature-extraction` for AutoModel, `fill-mask` for AutoModelForMaskedLM, `image-classification` for AutoModelForImageClassification, `image-segmentation` for ('AutoModelForImageSegmentation', 'AutoModelForSemanticSegmentation'), `image-to-image` for AutoModelForImageToImage, `image-to-text` for ('AutoModelForVision2Seq', 'AutoModel'), `mask-generation` for AutoModel, `masked-im` for AutoModelForMaskedImageModeling, `multiple-choice` for AutoModelForMultipleChoice, `object-detection` for AutoModelForObjectDetection, `question-answering` for AutoModelForQuestionAnswering, `reinforcement-learning` for AutoModel, `semantic-segmentation` for AutoModelForSemanticSegmentation, `text-to-audio` for ('AutoModelForTextToSpectrogram', 'AutoModelForTextToWaveform'), `text-generation` for AutoModelForCausalLM, `text2text-generation` for AutoModelForSeq2SeqLM, `text-classification` for AutoModelForSequenceClassification, `token-classification` for AutoModelForTokenClassification, `zero-shot-image-classification` for AutoModelForZeroShotImageClassification, `zero-shot-object-detection` for AutoModelForZeroShotObjectDetection"

comes from the fact that we don't yet support the "image-text-to-text" task but can be added here

optimum/optimum/exporters/tasks.py

Line 203 in d21256c

_TRANSFORMERS_TASKS_TO_MODEL_LOADERS = {

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added in marcindulak@ea2321c

"image-to-text",
onnx="GITOnnxConfig",
),
"glpn": supported_tasks_mapping(
"feature-extraction",
"depth-estimation",
Expand Down
8 changes: 8 additions & 0 deletions tests/exporters/exporters_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,14 @@
},
"flaubert": "hf-internal-testing/tiny-random-flaubert",
"gemma": "fxmarty/tiny-random-GemmaForCausalLM",
"git": {
"hf-internal-testing/tiny-random-GitModel": [
"feature-extraction",
],
"hf-internal-testing/tiny-random-GitForCausalLM": [
"image-text-to-text",
],
},
"glpn": "hf-internal-testing/tiny-random-GLPNModel",
"gpt2": "hf-internal-testing/tiny-random-gpt2",
"gpt-bigcode": "hf-internal-testing/tiny-random-GPTBigCodeModel",
Expand Down
8 changes: 8 additions & 0 deletions tests/onnxruntime/utils_onnxruntime_tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,14 @@
"flaubert": "hf-internal-testing/tiny-random-flaubert",
"flux": "optimum-internal-testing/tiny-random-flux",
"gemma": "fxmarty/tiny-random-GemmaForCausalLM",
"git": {
"hf-internal-testing/tiny-random-GitModel": [
"feature-extraction",
],
"hf-internal-testing/tiny-random-GitForCausalLM": [
"image-text-to-text",
],
},
"gpt2": "hf-internal-testing/tiny-random-gpt2",
"gpt_bigcode": "hf-internal-testing/tiny-random-GPTBigCodeModel",
"gpt_neo": "hf-internal-testing/tiny-random-GPTNeoModel",
Expand Down