Comments (8)
Hi, firstly, UCF-101 does provide the official split for training and testing (but there are several splits to prevent overfitting). Could you please try the experiments on split 1 to get the results?
from temporal-shift-module.
@tonylins Hi, thanks. Do you mean I should train on the whole UCF101 dataset and test on split1?
from temporal-shift-module.
@Jaychoukobbe No. You should split the dataset into train and eval according to split1.
from temporal-shift-module.
@tonylins Thanks, but I dont really konw waht you mean. Firstly, I download the three train/test split files from UCF101 dataset official site and as I can see, each train/test split splits the dataset in different way.
So what do u mean that "split the dataset into train and eval according to split1"? Does it differ from the original split1 which I download.
I really need to reproduce this result, thanks for your help!!
from temporal-shift-module.
@tonylins And can you share your train/val/test split files with me? Thanks very much.
from temporal-shift-module.
Hi, for UCF-101, people usually perform experiments on the 3 splits and report the average accuracy to reduce over-fitting. You just need to convert the format of the 3 pairs of (train_list, test_list).
from temporal-shift-module.
@tonylins @Jaychoukobbe Hi, I also finetune the TSM_kinetics_RGB_resnet50_shift8_blockres_avg_segment8_e50.pth on UCF101 split 1 using the command below:
'''
python main.py ucf101 RGB
--arch resnet50 --num_segments 8
--gd 20 --lr 0.001 --lr_steps 10 20 --epochs 25
--batch-size 64 -j 16 --dropout 0.8 --consensus_type=avg --eval-freq=1
--shift --shift_div=8 --shift_place=blockres
--tune_from=pretrained/TSM_kinetics_RGB_resnet50_shift8_blockres_avg_segment8_e50.pth
'''
but I change the batch_size to be 32, and try the experiments using lr 0.001 and 0.0005, finally, I test the model using the command below:
'''
python test_models.py ucf101
--weights=checkpoint/TSM_ucf101_RGB_resnet50_shift8_blockres_avg_segment8_e25/ckpt.best.pth.tar
--test_segments=8 --batch_size=72 -j 24 --test_crops=3 --twice_sample --full_res
'''
but I just get Acc@1 88.84%,it is much worse than 95.9% and 93.4%, so I want to know what I need to do besides that, and if you got Acc@1 95.9% by using rgb&flow fusion.
Thanks.
from temporal-shift-module.
@GoodMan0 did you solve it ? I use TSM_kinetics_RGB_resnet50_shift8_blockres_avg_segment8_e50.pth to finetune UCF101 ,and it only got 87% when training,and also about 87% by using the test_models.py
from temporal-shift-module.
Related Issues (20)
- Question on online google maps HOT 1
- Unable to understand average_duration > 0 and record.num_frames > self.num_segments: HOT 1
- nvidia
- Excuse me, the parameters controlling the time shift are false. Where can I call them
- Acc1 about training HMDB51 pretrained on Imagenet HOT 5
- Rebuild DPU kernel
- Trying to understand fold_div
- Can not download the pretrained models HOT 3
- How to set up the correct combination of shift_div and frame_count? HOT 1
- the pretrained model link is broken. It shows as text but not downloading HOT 2
- How to extract my own dataset and where is the pre-trained model?
- Question about online demo
- On the precision of something-something-v1
- Confusion about the parameter.
- nll_loss_forward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [0,0,0] Assertion `t >= 0 && t < n_classes` failed.
- questions about raspberrypi
- TSM model checkpoint download links not working HOT 2
- Which parameter in the code corresponds to the channel shift ratio? Is it 'shift_div'?
- How to train pretrain model with Kinetics dataset? About choosing parameters
- TypeError: 'IntImm' object cannot be interpreted as an integer
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 temporal-shift-module.