Comments (13)
have you tried the linear prob eval?
from mae-pytorch.
Emm, how about end-to-end finetuning?
from mae-pytorch.
I just tried your latest updata of end-to-end finetuning, it seems good. But I think linear prob still is a metric cannot avoided.
from mae-pytorch.
Thanks for you suggestions, we actually ignore the linear prob metric. In fact, I am not very familiar with Linear Prob. Can you help me try to implement it? Thank you very much!
from mae-pytorch.
https://github.com/facebookresearch/dino/blob/main/eval_linear.py
dino contains the code of knn and linear eval code. I am not sure how to treat the cls token, as the linear prob only finetune the last head, but for MAE , the cls token is not pre-trained.
from mae-pytorch.
Ok, thank you~
from mae-pytorch.
Hello, have you finished the end-to-end fine-tuning of vit-base/1600e? Can you tell me the result? Thank you!
from mae-pytorch.
Hi, I finished the epoch 1600 training, but I only got fine-tuning result of 83.15 for epoch 1400 and 82.97 for epoch 1600. which is lower than your reported epoch 400 and the paper results.
from mae-pytorch.
From your pretrained log of vit_base, I found your max learning rate is 0.0024, is you run with 128X32 batch size?
according to the code: args.lr = args.lr * total_batch_size / 256, which should be 0.0006 for batchsize of 128X8.
from mae-pytorch.
Ok, that is very strange. I run vit-base with 512 x 8 = 4096, where the lr: 1.5e-4 * 512 * 8 / 256 = 0.0024.
from mae-pytorch.
ok, I will try your setting to reimplement your results for epoch 400. But the results of epoch 1600 is on batchsize 4096, still not good enough. the ft accuracy incrase slowly with epoch: 82.71/200, 82.82/400,82.87/600, 83/800,82.78/1000,82.96/1200,83.15/1400,82.97/1600.
from mae-pytorch.
OK, thank you for your so much experiments!
Maybe there is still some problems, I will check it carefully.
from mae-pytorch.
@Dongshengjiang Have you tried the LinearProbe evaluation with cls token?
The paper said: As ViT has a class token [16], to adapt to this design, in our MAE pre-training we append an auxiliary dummy token to the encoder input. This token will be treated as the class token for training the classifier in linear probing and fine-tuning.
It seems that the author just adds a dummy token when pre-training, and directly uses it as the feature for linear probing.
from mae-pytorch.
Related Issues (20)
- Bad transfer learning result while fine tuning in iNaturalist 2019 which is not IN1K HOT 7
- Is the finetune script doing an end2end finetune, not just linear-porbing? HOT 1
- A little suggestion about data HOT 1
- Question upon MSE loss HOT 1
- Do I need to specify the value of mask_ratio before finetune?
- training with 400 epoch has IndexError when training at the last iteration
- Which dataset is used for the released pretrained model?
- A warning when pretraining HOT 2
- Pretrained weight of vit-S
- Patch size for pretraining
- learning rate curve
- Visualize Problems HOT 2
- How to resume from the checkpoint?
- SimMIM test
- I wonder if you plan to release the mask prediction visualization code?
- RuntimeError: Given normalized_shape=[768], expected input with shape [*, 768], but got input of size[12]
- Visual loading model error HOT 6
- How to implement Layer-wise learning rate decay on ResNet?
- Error reported in code finetune, AttributeError: 'VisionTransformer' object has no attribute 'get_num_layers'.
- The import accimage cannot be parsed
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 mae-pytorch.