qianyuzqy / transvod_plusplus Goto Github PK
View Code? Open in Web Editor NEW(TPAMI 2023) TransVOD:End-to-End Video Object Detection with Spatial-Temporal Transformers (implementations of TransVOD++).
License: Apache License 2.0
(TPAMI 2023) TransVOD:End-to-End Video Object Detection with Spatial-Temporal Transformers (implementations of TransVOD++).
License: Apache License 2.0
Hi, congrats on your work.
Can you please share the code for generating Fig.7
When I try to train using the Swins model, I get the following error.
RuntimeError: Given groups=1, weight of size [256, 1024, 1, 1], expected input[15, 768, 10, 32] to have 1024 channels, but got 768 channels instead
swins_train_multi.sh
set -x
T=`date +%m%d%H%M`
EXP_DIR=exps/multibaseline_level256_agg256_tdtd/swin_grad_88.3_e7_l56/e6_nf1_ld4,5_lr0.0002_nq100_wbox_MEGA_detrNorm_preSingle_nr14_dc5_nql3_filter150_75_40
mkdir -p ${EXP_DIR}
PY_ARGS=${@:1}
python -u main.py \
--backbone swin_s_p4w7 \
--epochs 6 \
--num_feature_levels 1 \
--num_queries 100 \
--hidden_dim 256 \
--dilation \
--batch_size 1 \
--num_ref_frames 14 \
--num_workers 16 \
--with_box_refine \
--dataset_file 'vid_multi' \
--output_dir ${EXP_DIR} \
${PY_ARGS} 2>&1 | tee ${EXP_DIR}/log.train.$T
There is no problem with the training data because training was possible without any problems in the transvod baseline model.
ILSVRC2015 DET and ILSVRC2015 VID dataset, both are need? Can train this model successfully only with ILSVRC2015 VID?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.