Skip to content

Investigate argmax TypeError in facetorch issue 84 #87

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

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Investigate argmax TypeError in facetorch issue 84 #87

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
82998ff
Support tuple input in PostArgMax post-processor
cursoragent Aug 1, 2025
cb8193e
Remove paperswithcode badges from README
cursoragent Aug 1, 2025
7b8f775
Fix flake8 linting: remove trailing whitespace
cursoragent Aug 1, 2025
0d7eb55
Bump version to 0.6.1 and update CHANGELOG
cursoragent Aug 1, 2025
b5853a2
Update CHANGELOG.md
tomas-gajarsky Aug 1, 2025
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
11 changes: 11 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,16 @@
# Change Log

## 0.6.1

Released on August 1, 2025.

### Fixed
* PostArgMax post-processor to handle tuple inputs (resolves TypeError: argmax(): argument 'input' must be Tensor, not tuple)

### Changed
* Removed non-working paperswithcode badges from README for better readability


## 0.6.0

Released on May 24, 2025.
Expand Down
12 changes: 0 additions & 12 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,6 @@ analyzer
1. biubug6
* code: [Pytorch_Retinaface](https://github.com/biubug6/Pytorch_Retinaface)
* paper: [Deng et al. - RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild](https://openaccess.thecvf.com/content_CVPR_2020/html/Deng_RetinaFace_Single-Shot_Multi-Level_Face_Localisation_in_the_Wild_CVPR_2020_paper.html)
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/190500641/face-detection-on-wider-face-hard)](https://paperswithcode.com/sota/face-detection-on-wider-face-hard?p=190500641)



Expand All @@ -131,14 +130,10 @@ analyzer
1. Jung-Jun-Uk
* code: [UNPG](https://github.com/jung-jun-uk/unpg)
* paper: [Jung et al. - Unified Negative Pair Generation toward Well-discriminative Feature Space for Face Recognition](https://arxiv.org/abs/2203.11593)
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unified-negative-pair-generation-toward-well/face-verification-on-ijb-b)](https://paperswithcode.com/sota/face-verification-on-ijb-b?p=unified-negative-pair-generation-toward-well)(FAR=0.01)
* Note: ```include_tensors``` needs to be True in order to include the model prediction in Prediction.logits
2. mk-minchul
* code: [AdaFace](https://github.com/mk-minchul/adaface)
* paper: [Kim et al. - AdaFace: Quality Adaptive Margin for Face Recognition](https://arxiv.org/abs/2204.00964)
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/adaface-quality-adaptive-margin-for-face/face-verification-on-ijb-b)](https://paperswithcode.com/sota/face-verification-on-ijb-b?p=adaface-quality-adaptive-margin-for-face) <
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/adaface-quality-adaptive-margin-for-face/face-verification-on-ijb-c)](https://paperswithcode.com/sota/face-verification-on-ijb-c?p=adaface-quality-adaptive-margin-for-face) <
* < badges represent models trained on smaller WebFace 4M dataset
* Note: ```include_tensors``` needs to be True in order to include the model prediction in Prediction.logits


Expand All @@ -152,9 +147,6 @@ analyzer
1. HSE-asavchenko
* code: [face-emotion-recognition](https://github.com/HSE-asavchenko/face-emotion-recognition)
* paper: [Savchenko - Facial expression and attributes recognition based on multi-task learning of lightweight neural networks](https://ieeexplore.ieee.org/abstract/document/9582508)
* B2 [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/classifying-emotions-and-engagement-in-online/facial-expression-recognition-on-affectnet)](https://paperswithcode.com/sota/facial-expression-recognition-on-affectnet?p=classifying-emotions-and-engagement-in-online)
* B0 [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/facial-expression-and-attributes-recognition/facial-expression-recognition-on-affectnet)](https://paperswithcode.com/sota/facial-expression-recognition-on-affectnet?p=facial-expression-and-attributes-recognition)
* B0 [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/facial-expression-and-attributes-recognition/facial-expression-recognition-on-acted-facial)](https://paperswithcode.com/sota/facial-expression-recognition-on-acted-facial?p=facial-expression-and-attributes-recognition)

#### Facial Action Unit Detection (au)

Expand All @@ -165,7 +157,6 @@ analyzer
1. CVI-SZU
* code: [ME-GraphAU](https://github.com/CVI-SZU/ME-GraphAU)
* paper: [Luo et al. - Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition](https://arxiv.org/abs/2205.01782)
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/learning-multi-dimensional-edge-feature-based/facial-action-unit-detection-on-bp4d)](https://paperswithcode.com/sota/facial-action-unit-detection-on-bp4d?p=learning-multi-dimensional-edge-feature-based)
* ! Does not work with CUDA > 12.0

#### Facial Valence Arousal (va)
Expand Down Expand Up @@ -198,9 +189,6 @@ for Identity-invariant Facial Expression Recognition](https://arxiv.org/abs/2209
1. choyingw
* code: [SynergyNet](https://github.com/choyingw/SynergyNet)
* challenge: [Wu et al. - Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry](https://arxiv.org/abs/2110.09772)
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/synergy-between-3dmm-and-3d-landmarks-for/face-alignment-on-aflw)](https://paperswithcode.com/sota/face-alignment-on-aflw?p=synergy-between-3dmm-and-3d-landmarks-for)
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/synergy-between-3dmm-and-3d-landmarks-for/head-pose-estimation-on-aflw2000)](https://paperswithcode.com/sota/head-pose-estimation-on-aflw2000?p=synergy-between-3dmm-and-3d-landmarks-for)
* [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/synergy-between-3dmm-and-3d-landmarks-for/face-alignment-on-aflw2000-3d)](https://paperswithcode.com/sota/face-alignment-on-aflw2000-3d?p=synergy-between-3dmm-and-3d-landmarks-for)
* Note: ```include_tensors``` needs to be True in order to include the model prediction in Prediction.logits


Expand Down
7 changes: 5 additions & 2 deletions facetorch/analyzer/predictor/post.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,15 +103,18 @@ def __init__(
self.dim = dim

@Timer("PostArgMax.run", "{name}: {milliseconds:.2f} ms", logger=logger.debug)
def run(self, preds: torch.Tensor) -> List[Prediction]:
def run(self, preds: Union[torch.Tensor, Tuple[torch.Tensor]]) -> List[Prediction]:
"""Post-processes the prediction tensor using argmax and returns a list of prediction data structures, one for each face.

Args:
preds (torch.Tensor): Batch prediction tensor.
preds (Union[torch.Tensor, Tuple[torch.Tensor]]): Batch prediction tensor.

Returns:
List[Prediction]: List of prediction data structures containing the predicted labels and confidence scores for each face in the batch.
"""
if isinstance(preds, tuple):
Copy link
Preview

Copilot AI Aug 1, 2025

Choose a reason for hiding this comment

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

Consider adding a check for empty tuples to prevent potential IndexError when accessing preds[0]. An empty tuple would cause the next line to fail.

Suggested change
if isinstance(preds, tuple):
if isinstance(preds, tuple):
if len(preds) == 0:
# Handle empty tuple gracefully, e.g., return empty list
return []

Copilot uses AI. Check for mistakes.

preds = preds[0]

indices = torch.argmax(preds, dim=self.dim).cpu().numpy().tolist()
pred_list = self.create_pred_list(preds, indices)

Expand Down
2 changes: 1 addition & 1 deletion version
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
0.6.0
0.6.1
Loading