By Byungseok Roh*, Jaewoong Shin*, Wuhyun Shin*, and Saehoon Kim at Kakao Brain. (*: Equal contribution)
The code will be updated soon.
Hi! Thank you for releasing such a wonderful work. How DAM is generated was a bit unclear to me when reading the paper. Assuming there are N tokens in total from the encoder (considering one feature level, then N = H x W), and M object queries:
N x M?Thanks! I look forward to your reply.
When I try to test with the pre-trained model, an error reported matrix contains invalid numeric entries, due to backbone output is nan, is there any solution?
RuntimeError: 0INTERNAL ASSERT FAILED at "/opt/conda/conda-bld/pytorch_1639180594101/work/torch/csrc/jit/ir/alias_analysis.cpp":584, please report a bug to PyTorch. We don't have an op for aten::fill_ but it isn't a special case. Argument types: Tensor, bool,
What does the structure of the scoring network consist of? The paper only describes that the scoring network is the same as the detection head of the decoder, is it all the same? Thank you for your help!
Hello, nice work! In your repo, I find that the AP of swin-t detr is reported. Would you like to kindly offer the checkpoint of 500-epoch swin-t detr with AP of 45.4? Looking for your reply! Cordially, Sean
TL;DR ) Fixed util/misc.py's version checking method for torchvision to be compatible with torchvision >= 0.10.0
Since I was interested in your paper, Sparse DETR, I was trying to run(train/test) model within Google Colab environment.
During the initial run, I found out that torchvision version checking method does not work as intended:
torchvision version was0.10.1, but the checking method treated as 0.1.Solved by replacing
float(torchvision.__version__[:3]) < 0.5
with
float(torchvision.__version__.split('.')[1]) < 5
And for <0.7, similarly fixed.
Therefore, I request pull-request to fix this issue.
Thank you. Taewoo Jeong.
If my understanding is correct, when you do:
self.class_embed = nn.Linear(hidden_dim, num_classes)
at DeformableDETR() in deformable_detr.py, "num_classes" should instead be "num_classes + 1"
The same thing goes for:
self.class_embed.bias.data = torch.ones(num_classes) * bias_value
in the same DeformableDETR() function, where it should be "num_classes + 1" instead of "num_classes".
Otherwise I'm just getting confused somewhere, but I'm pretty sure there should be an extra background class logit.
That is how it was done in the original DETR code anyways.
Differentiable Neural Computers and family, for Pytorch Includes: Differentiable Neural Computers (DNC) Sparse Access Memory (SAM) Sparse Differentiab
PyTorch Implementation of Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers 1 Using Colab Please notic
OW-DETR: Open-world Detection Transformer (CVPR 2022) [Paper] Akshita Gupta*, Sanath Narayan*, K J Joseph, Salman Khan, Fahad Shahbaz Khan, Mubarak Sh
The DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings and that the spatial embeddings make minor contributions, increasing the need for high-quality content embeddings and thus increasing the training difficulty.
UP-DETR: Unsupervised Pre-training for Object Detection with Transformers This is the official PyTorch implementation and models for UP-DETR paper: @a
PED: DETR for Crowd Pedestrian Detection Code for PED: DETR For (Crowd) Pedestrian Detection Paper PED: DETR for Crowd Pedestrian Detection Installati
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
Moment-DETR QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries Jie Lei, Tamara L. Berg, Mohit Bansal For dataset de
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations This is the official PyTorch implementation
SGLKT-VisDial Pytorch Implementation for the paper: Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer Gi-Cheon Kang, Junseok P
Image Super-Resolution with Non-Local Sparse Attention This repository is for NLSN introduced in the following paper "Image Super-Resolution with Non-
Sparse deconvolution Python v0.3.0 Official Python implementation of the 'Sparse deconvolution', and the CPU (NumPy) and GPU (CuPy) calculation backen
Sparse-dense operators implementation for Paddle This module implements coo, csc and csr matrix formats and their inter-ops with dense matrices. Feel
Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors (CVPR 2022) Personal Web Pages | Paper | Project Page This repository contains
The DeepSparse Engine is a CPU runtime that delivers unprecedented performance by taking advantage of natural sparsity within neural networks to reduce compute required as well as accelerate memory bound workloads. It is focused on model deployment and scaling machine learning pipelines, fitting seamlessly into your existing deployments as an inference backend.
QueryDet-PyTorch This repository is the official implementation of our paper: QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small O
CondenseNetV2 This repository is the official Pytorch implementation for "CondenseNet V2: Sparse Feature Reactivation for Deep Networks" paper by Le Y
Submanifold Sparse Convolutional Networks This is the PyTorch library for training Submanifold Sparse Convolutional Networks. Spatial sparsity This li
Movement Pruning: Adaptive Sparsity by Fine-Tuning Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; ho
302 Dec 14, 2022
489 Jan 7, 2023
127 Dec 27, 2022
281 Dec 30, 2022
430 Dec 23, 2022
36 Sep 13, 2022
2k Jan 5, 2023
133 Dec 22, 2022
42 Nov 9, 2022
9 Jul 5, 2022
143 Dec 28, 2022
23 Dec 28, 2022
3 Dec 17, 2022
151 Dec 26, 2022
1.2k Jan 9, 2023
276 Dec 31, 2022
74 Dec 12, 2022
1.8k Jan 6, 2023
54 Dec 20, 2022