Comments (4)
the paper give the exp of imagenet1k however this repo seem to train in imagenet.
from mae.
For clarification, here ImageNet is ImageNet1K.
from mae.
@endernewton Whether ImageNet1K is imagenet with 1000 classes or imagenet with 1000 training images? I found the paper[https://arxiv.org/pdf/2104.10972.pdf]: ImageNet-1K is a subset of the full ImageNet dataset [11], which consists of
14,197,122 images, divided into 21,841 classes. ImageNet-1K
was created by selecting a subset of 1.2M images from ImageNet-21K, that belong to 1000 mutually
exclusive classes.
from mae.
I have a very very basic question: which one is the ImageNet-1K on ImageNet's official website (https://image-net.org/download-images.php)? Since I only found the link of ImageNet21K and ILSVRC 2012-2017. I tried to download ILSVRC 2012, and the structure is a little bit difference with the Data preparation:
/path/to/imagenet/
train/
class1/
img1.jpeg
class2/
img2.jpeg
val/
class1/
img3.jpeg
class2/
img4.jpeg
in https://github.com/facebookresearch/deit/blob/main/README_deit.md. The train folder is correct, but the val folder is different: There is no class level folder.
ILSVRC2012_img_val/
img1.jpeg
img2.jpeg
img3.jpeg
Sorry I'm a rookie in CV.
from mae.
Related Issues (20)
- param_groups_lrd for layer decay HOT 1
- Loss is considerably worse on custom data set with different mean and standard deviation HOT 2
- Error in loading pretrained weight for 'mae_vit_base_patch16' HOT 2
- About the gan-loss HOT 2
- patchify and unpatchify HOT 1
- I found both LLAMA and MAE used smaller beta2 in ADAMW optimizer during pre-training. Is that any intuition behind such setting? HOT 1
- How to obtain the reconstructed image for inference and masked
- model.fc_norm is not trained in linear probing
- visualization attention map.
- Could you provide the pretrained checkpoints of both encoder and decoder in MAE? HOT 2
- Is the training procedure result normal? Masked regions do not improve and appear to be random noise. HOT 2
- Two different checkpoints for each ViT type HOT 5
- Code: Compatible to any channels for function patchify and unpatchify HOT 2
- collab notebook error HOT 2
- How to obtain the complete reconstructed image?
- Can run interactive visualization demo with GPU?
- 训练的代码用最新的timm跑不通
- Reconstruction using normalized pixel values to get unnormalized pixel values?
- 不匹配
- Bug in `random_masking`?
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.