Comments (5)
oh, I discovered that when I tried using VGG (obtained from UMT) features, the model also failed to learn effectively. It only worked when using SlowFast + Clip features.
from qd-detr.
the configuration as follows:
dset_name=charades
ctx_mode=video_tef
v_feat_types=c3d
t_feat_type=clip
results_root=results
exp_id=exp
if [[ ${v_feat_types} == *"c3d"* ]]; then
v_feat_dirs+=(${feat_root}/charades_c3d_raw)
(( v_feat_dim += 1024 ))
fi
if [[ ${v_feat_types} == *"rgb"* ]]; then
v_feat_dirs+=(${feat_root}/charades_rgb_opt/rgb_features)
(( v_feat_dim += 4096 ))
fi
bsz=32
n_epoch=100
lr_drop=40
lr=0.0002
lw_saliency=4.0
max_v_l=-1
max_q_l=32
clip_length=1
PYTHONPATH=$PYTHONPATH:. python qd_detr/train.py \
--dset_name ${dset_name} \
--ctx_mode ${ctx_mode} \
--train_path ${train_path} \
--eval_path ${eval_path} \
--eval_split_name ${eval_split_name} \
--v_feat_dirs ${v_feat_dirs[@]} \
--v_feat_dim ${v_feat_dim} \
--t_feat_dir ${t_feat_dir} \
--t_feat_dim ${t_feat_dim} \
--bsz ${bsz} \
--n_epoch ${n_epoch} \
--lr_drop ${lr_drop} \
--lr ${lr} \
--lw_saliency ${lw_saliency} \
--max_v_l ${max_v_l} \
--max_q_l ${max_q_l} \
--clip_length ${clip_length} \
--results_root ${results_root}_charades \
--exp_id ${exp_id} \
${@:1}
from qd-detr.
Sorry for bothering you. I have resolved the issue. I overlooked the fact that different features corresponded to different clip lengths.
from qd-detr.
Great! Thanks.
from qd-detr.
We are very sorry for the inconvenience.
Charades-STA experiments with C3D features are actually conducted with I3D features and I3D benchmarking tables.
Features are provided here from VSLNET.
from qd-detr.
Related Issues (20)
- Eval HOT 1
- Can not completely reproduce reported video-only results on QVHighlights with the default configs HOT 2
- what does parameter 'clip_len' mean? HOT 2
- the feature about charades-sta HOT 3
- a very unreasonable phenomenon HOT 7
- about feature extract HOT 2
- The implement of rank-aware contrastive loss HOT 2
- What does parameter "use_tef" mean? HOT 2
- At training, RuntimeError: The size of tensor a (148) must match the size of tensor b (150) at non-signleton dimesnion 1
- Confusion about the code HOT 1
- TypeError: unsupported operand type(s) for /: 'dict' and 'float' HOT 4
- The I3D features about Charades-STA HOT 3
- Training Machine Question HOT 1
- Charades dataset feature
- Training on Charades-STA dataset with VGG backbone HOT 10
- Fail to download TVsum dataset and could you please provide a new link๏ผ HOT 2
- TVSUM Result HOT 2
- TVSUM data issue HOT 4
- SharePoint: That didn't work - user cannot be found in the directory HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from qd-detr.