Comments (9)
Hi chen,
Can you share your settings for reference?My training doesn 't work, I ' d like to refer to your settings for UCF101 and HMDB51.
from videomae.
Hi Jianyu,
Here's my seetings for HMDB51 on 8 GPUs 1 Server:
OMP_NUM_THREADS=1 python -m torch.distributed.launch --nproc_per_node=8
--master_port 12320
run_mae_pretraining.py
--data_path ${DATA_PATH}
--mask_type tube
--mask_ratio 0.9
--model pretrain_videomae_base_patch16_224
--decoder_depth 4
--batch_size 24
--num_frames 16
--sampling_rate 2
--opt adamw
--opt_betas 0.9 0.95
--warmup_epochs 40
--save_ckpt_freq 100
--epochs 4800
--log_dir ${OUTPUT_DIR}
--output_dir ${OUTPUT_DIR}
--lr 3e-4
The setting for UCF101 is similar, only need to modify the epochs number to 3200 and sampling_rate to 4.
from videomae.
from videomae.
For UCF101:
OMP_NUM_THREADS=1 python -m torch.distributed.launch --nproc_per_node=8
--master_port 12320
run_class_finetuning.py
--model vit_base_patch16_224
--data_set UCF101
--nb_classes 101
--data_path ${DATA_PATH}
--finetune ${MODEL_PATH}
--log_dir ${OUTPUT_DIR}
--output_dir ${OUTPUT_DIR}
--batch_size 8
--update_freq 2
--num_sample 1
--input_size 224
--short_side_size 224
--save_ckpt_freq 10
--num_frames 16
--sampling_rate 4
--opt adamw
--lr 1e-3
--opt_betas 0.9 0.999
--weight_decay 0.05
--epochs 100
--dist_eval
--test_num_segment 5
--test_num_crop 3
--enable_deepspeed
# --eval
from videomae.
Thank you for your reply, if I want to set batch size to 8, LR need to be changed?
from videomae.
Thank you for your reply, if I want to set batch size to 8, LR need to be changed?
For the finetuning, I set --batch_size 8 and --update_freq 2, so theoretically I am training the model with 128 batches on 8 GPUs. But if you want to use a different total batch size, you may need to tune the LR for better results.
from videomae.
Hi, @chenliz1, could you share the time it takes to pre-train on HMDB51 and UCF101 in your setting? Besides, what is your reproduced result on UCF101? Thanks!
from videomae.
Hi, @chenliz1 , can you tell me how to process UCF101 dataset?What the data format looks like?Looking forward to your reply!
from videomae.
Hi @chenliz1 @jianyulei1 @youcaiSUN @Morning-YU ! The pre-trained models and scripts on UCF101 are available! Scripts on HMDB51 are coming soon!
from videomae.
Related Issues (20)
- Issue Encountered When Loading the Model: "pretrain_videomae_base_patch16_224" HOT 5
- ModuleNotFoundError: No module named 'petrel_client'
- License of Kinetics-400
- video xxx not correctly load during training
- The GPU memory usage of UCF and Kinetics is different.
- TODO/videomae_pretrain_base_patch16_224_frame_16x4_tube_mask_ratio_0.9_e1600/checkpoint-1599.pth HOT 1
- HMDB checkpoint
- Rebuild Video
- the numberi of rebuild images is too small
- AttributeError: module 'torch._C' has no attribute '_get_privateuse1_backend_name'
- How to obtain the reconstructed image for inference and masked
- How good model handle the different duration of clips?
- How to convert .pth to .bin HOT 1
- KeyError: 'model' HOT 2
- VideoMAE might not be a useful model for video reconstruction? Or perhaps it only learns the most generic distribution within patches? HOT 2
- How to use VideoMAE for video regression task?
- ucf101,hmdb51 HOT 1
- After obtaining the .pth file from training, how do I convert it into a .bin file for performing inference?
- 关于微调损失函数 HOT 1
- How to conduct zero-shot evaluations?
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 videomae.