Comments (5)
good work, I achieve perforemance of CUB-200-2011(92.3%), but I only got 93.73% on stanfordcars. Is it any other different configure compared with CUB-200-2011 except for lr?
from metaformer.
In my experiment, lr had the greatest impact on the experimental results. Try --lr 5e-3 --min-lr 5e-7 --warmup-lr 5e-8 --epochs 300 --warmup-epochs 20
with batchsize 512?
from metaformer.
In my experiment, lr had the greatest impact on the experimental results. Try
--lr 5e-3 --min-lr 5e-7 --warmup-lr 5e-8 --epochs 300 --warmup-epochs 20
?
python3 -m torch.distributed.launch --nproc_per_node 2 --master_port 12335 main.py --cfg ./configs/MetaFG_1_224.yaml --batch-size 32 --tag stcar_v2 --lr 5e-3 --min-lr 5e-7 --warmup-lr 5e-8 --epochs 300 --warmup-epochs 20 --dataset stanfordcars --pretrain ./pretrained_model/metafg_1_inat21_384.pth --accumulation-steps 8 --opts DATA.IMG_SIZE 384.
This is my config. I did use the recommended lr. Is it other different with cub-200-2011?
from metaformer.
In my experiment, lr had the greatest impact on the experimental results. Try
--lr 5e-3 --min-lr 5e-7 --warmup-lr 5e-8 --epochs 300 --warmup-epochs 20
?
python3 -m torch.distributed.launch --nproc_per_node 2 --master_port 12335 main.py --cfg ./configs/MetaFG_1_224.yaml --batch-size 32 --tag stcar_v2 --lr 5e-3 --min-lr 5e-7 --warmup-lr 5e-8 --epochs 300 --warmup-epochs 20 --dataset stanfordcars --pretrain ./pretrained_model/metafg_1_inat21_384.pth --accumulation-steps 8 --opts DATA.IMG_SIZE 384.
This is my config. I did use the recommended lr. Is it other different with cub-200-2011?
The actual training lr is related to batchsize, specifically actual_lr = lr * total_batchsize/512
from metaformer.
In my experiment, lr had the greatest impact on the experimental results. Try
--lr 5e-3 --min-lr 5e-7 --warmup-lr 5e-8 --epochs 300 --warmup-epochs 20
?
python3 -m torch.distributed.launch --nproc_per_node 2 --master_port 12335 main.py --cfg ./configs/MetaFG_1_224.yaml --batch-size 32 --tag stcar_v2 --lr 5e-3 --min-lr 5e-7 --warmup-lr 5e-8 --epochs 300 --warmup-epochs 20 --dataset stanfordcars --pretrain ./pretrained_model/metafg_1_inat21_384.pth --accumulation-steps 8 --opts DATA.IMG_SIZE 384.
This is my config. I did use the recommended lr. Is it other different with cub-200-2011?The actual training lr is related to batchsize, specifically actual_lr = lr * total_batchsize/512
Recommanded config includes --nproc_per_node 8 --batch-size 32 --accumulation-steps 2
. There are only 2*3090 for me, So I modify these into --nproc_per_node 2 --batch-size 32 --accumulation-steps 8
to maintain same total_batchsize. Is it right? I also notad ``fused_weight_gradient_mlp_cuda module not found. gradient accumulation fusion with weight gradient computation disabled.
in my log file. Dose it mean that `--accumulation-steps` dose not work in my code?
from metaformer.
Related Issues (20)
- bert_embedding_cub HOT 5
- Checkpoint on iNaturalist 2018
- Training time on inaturalist HOT 1
- About running on one GPU HOT 1
- RuntimeError in HOT 2
- About how to get meta data? HOT 1
- CUDA Version?
- Some errata found on the code HOT 2
- meta data HOT 2
- about pre-trained checkpoint
- about the checkpoint without meta info HOT 1
- metadata-generation-failed
- Apex and Cuda Version
- bert_embedding_cub HOT 1
- About how to get meta data?
- model weights for MetaFormer-2 fine tuned on iNat 2018
- Hello, thank you for the achievement I have a problem with using the cub attribute can you provide the run config parameter of the property, thank you very much HOT 1
- For CUB-200 meta data, i wonder know where is the bert_embedding_cub in the link of CUB-200 HOT 1
- Cannot load pretrain metafg_2_inat21_384 HOT 1
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 metaformer.