Add DETR Example - #47
Open
Jiang-Stan wants to merge 2 commits into
Open
Conversation
Jiang-Stan
force-pushed
the
support_detr_example
branch
4 times, most recently
from
September 9, 2022 07:07
cf37a4b to
9eafb44
Compare
Jiang-Stan
force-pushed
the
support_detr_example
branch
from
October 11, 2022 04:28
9eafb44 to
9768dfc
Compare
Jiang-Stan
force-pushed
the
support_detr_example
branch
2 times, most recently
from
October 18, 2022 09:07
9b211e5 to
2ae66e8
Compare
Jiang-Stan
force-pushed
the
support_detr_example
branch
2 times, most recently
from
November 9, 2022 08:55
321ff8e to
64c9260
Compare
PeiqinSun
reviewed
Nov 10, 2022
PeiqinSun
reviewed
Nov 10, 2022
|
|
||
| import util.misc as utils | ||
| from datasets.coco_eval import CocoEvaluator | ||
| from datasets.panoptic_eval import PanopticEvaluator |
Collaborator
Author
There was a problem hiding this comment.
sys.path.append("./detr") is added to main.py, so datasets used here is detr.datasets
Jiang-Stan
force-pushed
the
support_detr_example
branch
2 times, most recently
from
November 24, 2022 10:02
13717ca to
b022b39
Compare
Jiang-Stan
force-pushed
the
support_detr_example
branch
from
November 24, 2022 10:13
b022b39 to
be2c84f
Compare
PeiqinSun
reviewed
Nov 25, 2022
| out = F.hardsigmoid(x_in, inplace=self.inplace) | ||
| return out | ||
|
|
||
| @register_qmodule(sources=[nn.MultiheadAttention]) |
Member
There was a problem hiding this comment.
- You should build a new file to describe the QMHSA.
- the module name -- transformer.py
PeiqinSun
reviewed
Nov 25, 2022
| return attn_output, attn_output_weights | ||
|
|
||
| def prepare_input_quantizer(self, node, model): | ||
| # only qkv should be quantized. |
Jiang-Stan
force-pushed
the
support_detr_example
branch
from
November 29, 2022 12:35
89f64e5 to
4a70ee0
Compare
WIP WIP WIP Can test version Can test version modify for dump onnx ready version ready version ready version ready version ready version ready version update_readme add detr qat example fix bugs for qat update readme reformat dirs reformat dirs reformat dirs update readme rectify sparsebit move qat to another branch modify aciq observer and use aciq laplace for last 2 detr bbox embed weights update readme modifications for hugging DETR simplify MR simplify MR add detr as submodule detr as submodule detr as submodule detr as submodule detr as submodule rm qdropout rm redundant clean-up rebase modifications rebase modifications rebase modifications not finished yet not finished yet wrong version write but low_acc version finished version finished version finished version
Jiang-Stan
force-pushed
the
support_detr_example
branch
from
December 7, 2022 02:41
e0417a3 to
d1db231
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
DETR model from: https://github.com/facebookresearch/detr
Modifications to original model:
torch.fxdoesn't support.to(device)in forward function. (Details)