Comments (5)
I try it again and find that the version of timm influence so much.
when version of timm is 0.4.9, the acc is 72.03; when I change it the latest one, the acc is 75.376(matched with your result).
so, maybe there are some difference in the preprocessing part.
from van-classification.
I try to use the model downloaded from tsinghua cloud. However, i also get the 75.4 % acc.
The version of my softwares:
Pytorch == 1.7.1 (I heard it is important)
Timm == 0.4.12
from van-classification.
Amazing.
I download the model from google drive and can get the 75.4 % Acc.
Here is my eval command
I also load the model and print key. It is same with you.
from van-classification.
it's so strange! I tried the tiny and small, all not match. I also tried other model (vip and volo) and can got same acc as paper.
the model i tried was download from tsinghua cloud, i will try another one from google cloud later.
from van-classification.
I have the same problem, with Pytorch == 1.7.1 and Timm == 0.4.12
Loaded state_dict from checkpoint 'van_tiny_754.pth.tar'
Model van_tiny created, param count: 4105800
Data processing configuration for current model + dataset:
input_size: (3, 224, 224)
interpolation: bicubic
mean: (0.5, 0.5, 0.5)
std: (0.5, 0.5, 0.5)
crop_pct: 0.9
Test: [ 0/20] Time: 1.760s (1.760s, 113.65/s) Loss: 0.8368 (0.8368) Acc@1: 82.500 ( 82.500) Acc@5: 98.500 ( 98.500)
Test: [ 10/20] Time: 0.253s (0.469s, 426.49/s) Loss: 1.1970 (1.1323) Acc@1: 72.500 ( 76.636) Acc@5: 93.500 ( 94.364)
- Acc@1 74.586 (25.414) Acc@5 92.786 (7.214)
from van-classification.
Related Issues (20)
- [Question] Object detection and instance segmentation HOT 2
- When to use the freeze_patch_emb method HOT 3
- Question related to permutation operation used in the model HOT 1
- configuration for pre-trained models HOT 1
- Issue about training HOT 3
- The model used for classification problem HOT 2
- OverlapPatchEmbed HOT 6
- Why not use SyncBN HOT 2
- Code for detection HOT 1
- Why use .clone() for shortcut connection? HOT 1
- code for visualization
- RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED HOT 1
- 22k finetune 1k pretrained weights
- where is the detection model?
- Class activation mapping (CAM) Target Layer HOT 1
- how to understand large kernel convolution decomposition?
- Attention vs Add in LKA HOT 1
- question on the number of parameter HOT 1
- Decomposition diagram of large-kernel convolution
- Attention模块代码中的shortcut
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 van-classification.