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

[RT-Detr] - Add RT-Detr Onnx Config #2040

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

[RT-Detr] - Add RT-Detr Onnx Config #2040

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
8969e6c
Add RTDetr Onnx Config
YHallouard Oct 6, 2024
58d9548
add test and comment
YHallouard Oct 27, 2024
db800a3
merge main in feature branch
echarlaix Dec 17, 2024
29d380c
fix style
echarlaix Dec 17, 2024
1f71fae
Update tests large model
echarlaix Dec 17, 2024
f25f227
fix expected configs model type
echarlaix Dec 17, 2024
dd2a2a2
Merge branch 'main' into rt-detr-onnx
echarlaix Dec 19, 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
15 changes: 14 additions & 1 deletion optimum/exporters/onnx/model_configs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1793,7 +1793,8 @@ class SpeechT5OnnxConfig(OnnxSeq2SeqConfigWithPast):
# so we won't support for now.
NORMALIZED_CONFIG_CLASS = NormalizedSeq2SeqConfig.with_args(
hidden_size="hidden_size",
num_attention_heads="encoder_attention_heads", # TODO: bugged in case encoder and decoder have different number of heads
num_attention_heads="encoder_attention_heads",
# TODO: bugged in case encoder and decoder have different number of heads
encoder_num_layers="encoder_layers",
decoder_num_layers="decoder_layers",
allow_new=True,
Expand Down Expand Up @@ -2310,3 +2311,15 @@ def overwrite_shape_and_generate_input(

class EncoderDecoderOnnxConfig(EncoderDecoderBaseOnnxConfig):
NORMALIZED_CONFIG_CLASS = NormalizedEncoderDecoderConfig


class RTDetrOnnxConfig(ViTOnnxConfig):
DEFAULT_ONNX_OPSET = 16
echarlaix marked this conversation as resolved.
Show resolved Hide resolved
ATOL_FOR_VALIDATION = 1e-5

@property
def inputs(self) -> Dict[str, Dict[int, str]]:
return {
"pixel_values": {0: "batch_size", 1: "num_channels", 2: "height", 3: "width"},
"pixel_mask": {0: "batch_size"},
Copy link
Collaborator

@echarlaix echarlaix Dec 18, 2024 •
edited
Loading

Choose a reason for hiding this comment

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

why is it needed ? (not needed for ViT models but might be needed for RT-DETR)

Copy link
Collaborator

@echarlaix echarlaix Dec 18, 2024 •
edited
Loading

Choose a reason for hiding this comment

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

also if needed shouldn't the height / width dimension set to dynamic as well?

}
4 changes: 4 additions & 0 deletions optimum/exporters/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -994,6 +994,10 @@ class TasksManager:
onnx="RoFormerOnnxConfig",
tflite="RoFormerTFLiteConfig",
),
"rt-detr": supported_tasks_mapping(
"object-detection",
onnx="RTDetrOnnxConfig",
),
"sam": supported_tasks_mapping(
"feature-extraction",
onnx="SamOnnxConfig",
echarlaix marked this conversation as resolved.
Show resolved Hide resolved
Expand Down