shoufachen / comp3340_transformer_mlp Goto Github PK
View Code? Open in Web Editor NEWLicense: Apache License 2.0
License: Apache License 2.0
I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial Intelligence Conference in Shanghai. We invite you to upgrade your algorithm library to OpenMMLab 2.0 using MMEngine, which can be used for both research and commercial purposes. If you have any questions, please feel free to join us on the OpenMMLab Discord at https://discord.gg/amFNsyUBvm or add me on WeChat (van-sin) and I will invite you to the OpenMMLab WeChat group.
Here are the OpenMMLab 2.0 repos branches:
OpenMMLab 1.0 branch | OpenMMLab 2.0 branch | |
---|---|---|
MMEngine | 0.x | |
MMCV | 1.x | 2.x |
MMDetection | 0.x 、1.x、2.x | 3.x |
MMAction2 | 0.x | 1.x |
MMClassification | 0.x | 1.x |
MMSegmentation | 0.x | 1.x |
MMDetection3D | 0.x | 1.x |
MMEditing | 0.x | 1.x |
MMPose | 0.x | 1.x |
MMDeploy | 0.x | 1.x |
MMTracking | 0.x | 1.x |
MMOCR | 0.x | 1.x |
MMRazor | 0.x | 1.x |
MMSelfSup | 0.x | 1.x |
MMRotate | 1.x | 1.x |
MMYOLO | 0.x |
Attention: please create a new virtual environment for OpenMMLab 2.0.
As for the testing commands, the tools/test.py
will fail if we only specify the config-file
and the path-to-checkpoint
. After examining the source codes of the tools/tests.py, I observed at least one of the “out” or “metrics” options should be declared.
Thus, I modified the testing command as follows:
“`sh
python tools/test.py configs/vision_transformer/vit_base_patch16_224_flowers.py work_dirs/vit_base_patch16_224_flowers/latest.pth --metrics accuracy precision recall f1_score
I am not sure whether the execution result of my modification satisfies the design purpose of this section in the tutorial. Therefore, I would appreciate it if you could further review this command. Below are the outputs of my command:
![image](https://user-images.githubusercontent.com/43565614/156287244-d4cb2360-39ab-427d-8582-041f349ccce7.png)
In the tutorial notebook, section “Configuration”, a subsection is named “AutoAugmentation.” However, it seems unclear where these configurations should be placed.
After analyzing the repository structure, I believed this should be a part of the configs/vision_transformer/vit_base_patch16_224_flowers.py
file. In the codes you provided for our project group to develop our project, we found such configuration did appear there. We thought it might be more instructive and clear if the notebook could directly indicate the AutoAugmentation part of the vision transformer’s running configuration.
In the “Set saving config” subsection, we noticed there is an instruction:
However, the path here: mmclassification/configs/resnet/resnet18_flowers_bs128.py
is seemingly a bit misleading.
In our opinion, the config file ought to be configs/vision_transformer/vit_base_patch16_224_flowers.py
, instead. Otherwise, the path and the naming of the configuration file may not coordinate with the training command
python tools/train.py configs/vision_transformer/vit_base_patch16_224_flowers.py
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.