Comments (3)
Hi @xiao2mo, there is no special purpose. We set batch size 32 per GPU because some of our machines are 16G per card, and we need to test some other parameters like frame number. It is an appropriate batch size to finish the hyper-parameters study. If your card has more than 16G, a suggestion is to test a large frame number, then a large batch size.
from clip4clip.
I see it. The main problem in my exps is that batch size in DDP configuration may result in different results. Thank u.
from clip4clip.
hi
我这边是两张卡,每张卡是16G。
可是我能设置的batchsize是 16, 请问这是为什么呢?
训练配置如下
01/10/2022 16:18:00 - INFO - ***** Running test *****
01/10/2022 16:18:00 - INFO - Num examples = 497
01/10/2022 16:18:00 - INFO - Batch size = 16
01/10/2022 16:18:00 - INFO - Num steps = 32
01/10/2022 16:18:00 - INFO - ***** Running val *****
01/10/2022 16:18:00 - INFO - Num examples = 497
222
333
01/10/2022 16:18:12 - INFO - ***** Running training *****
01/10/2022 16:18:12 - INFO - Num examples = 130260
01/10/2022 16:18:12 - INFO - Batch size = 16
01/10/2022 16:18:12 - INFO - Num steps = 40705
01/10/2022 16:21:34 - INFO - Epoch: 1/5, Step: 50/8141, Lr: 0.000000001, Loss: 0.455173, Time/step: 4.041784
运行命令如下
python -m torch.distributed.launch --nproc_per_node=2 \
main_task_retrieval.py --do_train --num_thread_reader=0 \
--epochs=5 --batch_size=16 --n_display=50 \
--output_dir ckpts/ckpt_msrvtt_retrieval_looseType \
--lr 1e-4 --max_words 32 --max_frames 12 --batch_size_val 16 \
--datatype msrvtt --expand_msrvtt_sentences \
--feature_framerate 1 --coef_lr 1e-3 \
--freeze_layer_num 0 --slice_framepos 2 \
--loose_type --linear_patch 2d --sim_header meanP \
--pretrained_clip_name ViT-B/16
from clip4clip.
Related Issues (20)
- Use my own videos HOT 1
- Question about the calculation method of loss when there are multiple gpus HOT 1
- Results on MSRVTT and MSVD HOT 3
- running the project HOT 1
- Problem about reproducing the model HOT 1
- Reproduction on LSMDC DataSet HOT 6
- What do Pair, L, T stand for in the code? HOT 3
- How to use this repo to retrieve clips among videos by text?
- train dataset is shuffled regardless of seed
- AttributeError: Caught AttributeError in DataLoader worker process 0.
- Video-to-video retrieval?
- ValueError: Parameter config in `CLIP4Clip(config)` should be an instance of class `PretrainedConfig`. To create a model from a Google pretrained model use `model = CLIP4Clip.from_pretrained(PRETRAINED_MODEL_NAME)`
- Problem about Multi-GPU-Train architecture
- loss NaN when training on MSRVTT HOT 1
- About mean_pooling on text sequence HOT 2
- Evaluation batch
- Large performance drop if trained with fp32. HOT 1
- [PAD_TOKEN] is not used, but just adding 0
- train files HOT 1
- Directly pass the entire config as a argument to a function
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 clip4clip.