Comments (7)
You can refer to #25 for the jhmdb labels.
from yowo.
Thanks for the labels! I run the training procedure successfully.
But I have a new question that I can not reproduce the J-HMDB results.
After 25 epochs, I only get 65.07%, much lower than 74.4% shown in the paper.
AP: 98.33% (1)
AP: 98.74% (10)
AP: 97.78% (11)
AP: 39.40% (12)
AP: 40.06% (13)
AP: 94.73% (14)
AP: 71.47% (15)
AP: 30.06% (16)
AP: 31.94% (17)
AP: 14.99% (18)
AP: 45.34% (19)
AP: 22.74% (2)
AP: 71.97% (20)
AP: 64.42% (21)
AP: 91.01% (3)
AP: 76.60% (4)
AP: 94.07% (5)
AP: 57.49% (6)
AP: 56.25% (7)
AP: 69.93% (8)
AP: 99.21% (9)
mAP: 65.07%
And my jhmdb.cfg is
[net]
batch = 10
clip_duration = 16
height = 224
width = 224
channels = 3
momentum = 0.9
decay = 0.0005
learning_rate = 0.0001
max_batches = 100000
steps = 10000,20000,30000,40000
scales = 0.5,0.5,0.5,0.5
[region]
anchors = 0.95878, 3.10197, 1.67204, 4.0040, 1.75482, 5.64937, 3.09299, 5.80857$
classes = 21
num = 5
object_scale = 5
noobject_scale = 1
class_scale = 1
coord_scale = 1
my run_jhmdb-21.sh is
python train.py --dataset jhmdb-21 \
--data_cfg cfg/jhmdb21.data \
--cfg_file cfg/jhmdb21.cfg \
--n_classes 21 \
--backbone_3d resnext101 \
--backbone_3d_weights weights/pretrained/resnext-101-kinetics-hmdb51_split1.pth \
--freeze_backbone_3d \
--backbone_2d darknet \
--backbone_2d_weights weights/yolo.weights \
--freeze_backbone_2d \
Does anything go wrong? Or if there are somethings unknown for me to influence the results?
from yowo.
Moat probably the model is overfitting. Do not wait till the end of 25 epoch to run validation. Best performance is usually achieved between 5-10 epochs.
from yowo.
Moat probably the model is overfitting. Do not wait till the end of 25 epoch to run validation. Best performance is usually achieved between 5-10 epochs.
Can I use negative examples for the train? For example some actions without labels (for custom dataset)?
from yowo.
@ZZZZZZZZJ
Hi,
Could you share the J-HMDB21 labels to [email protected] ?
Thanks!
from yowo.
@ZZZZZZZZJ Have you successfully reproduced the ucf24 results reported in the paper?
from yowo.
@ZZZZZZZZJ Have you successfully reproduced the ucf24 results reported in the paper?
Same question.
from yowo.
Related Issues (20)
- Working on dataset other than humans HOT 3
- Can you provide each type of map in ava
- About the envs setup HOT 2
- KeyError: 'exp_avg' HOT 1
- YOWO not using GPUs? HOT 1
- model is None
- how is the yolo.weights trained?
- Training YOWO on a custom dataset HOT 1
- Dropbox links for pre-trained models for J-HMDB, UCF and their annotations give 404 error HOT 1
- The [email protected] results reported in the paper are for validation or test splits of the AVA dataset?
- A stronger YOWO achieved by us. HOT 4
- not find yowo_jhmdb21_32f_best.pth
- plz,how to make and train my own dataset?
- test_video_ava.py error
- ava_detection_val_boxes_and_labels.csv is missing
- ava_classnames.json is missing
- /usr/home/sut path HOT 1
- animal action reconginition
- Training YOWO on a customized dataset HOT 2
- This code lacks any Conda environment or usage instructions.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from yowo.