Comments (4)
Yes, we have modified the codes and hyper-parameters(For example, we will use layer-wise learning rate for better results in the new version and upload codes for SOTA imbalanced SSL algorithms).
We will upload new codes and logs/model checkpoints very soon. Besides, we will modify the results in the paper and will continuously update results if codes modified.
from semi-supervised-learning.
Hi, thanks for the reply, I hope it will be soon. Besides, can I ask about a text file ( './data/semi_fgvc/semi_aves/l_train_val.txt'
) required for Semi-AVES dataset? I downloaded the dataset from https://www.kaggle.com/c/semi-inat-2020, but I could not find this file anywhere.
Traceback (most recent call last):
File "train.py", line 364, in <module>
main(args)
File "train.py", line 73, in main
main_worker(args.gpu, ngpus_per_node, args)
File "train.py", line 118, in main_worker
dataset_dict = get_dataset(args, args.algorithm, args.dataset, args.num_labels, args.num_classes, args.seed, args.data_dir)
File "/local_ssd3/vinnamki/Semi-supervised-learning/semilearn/utils.py", line 117, in get_dataset
lb_dset, ulb_dset, eval_dset = get_semi_aves(args, algorithm, dataset, train_split='l_train_val', data_dir=data_dir)
File "/local_ssd3/vinnamki/Semi-supervised-learning/semilearn/datasets/cv_datasets/aves.py", line 47, in get_semi_aves
train_labeled_dataset = iNatDataset(alg, data_dir, train_split, dataset, transform=transform_weak)
File "/local_ssd3/vinnamki/Semi-supervised-learning/semilearn/datasets/cv_datasets/aves.py", line 103, in __init__
self.samples, self.num_classes, self.targets = make_dataset(self.dataset_root,
File "/local_ssd3/vinnamki/Semi-supervised-learning/semilearn/datasets/cv_datasets/aves.py", line 62, in make_dataset
with open(split_file_path, 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: './data/semi_fgvc/semi_aves/l_train_val.txt'
from semi-supervised-learning.
Hi vinnamkim,
We followed "A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification" for the dataset construction. The required file can be found here.
from semi-supervised-learning.
Updated in fb36c1c
from semi-supervised-learning.
Related Issues (20)
- I can't load model correctly HOT 1
- colab code can not run in Custom_Dataset.ipynb” HOT 1
- 为什么我在自己的数据集上面,100-600-1200不同的有标签数量训练之后,在测试集的效果是一样的差。 HOT 2
- SAT.ass HOT 1
- About config, how to decide the hyperparameters? HOT 3
- There seems to be something strange when the data is loading HOT 6
- Issues related to voice datasets HOT 1
- R..net..\..m..;M// HOT 1
- How to decide the number of labels in experiments HOT 1
- Questions about batch normalization handling. HOT 1
- Can this run a multilabel problem HOT 1
- Testing models on audio datasets HOT 1
- semilearn get config from file
- Semi-supervised-learning/semilearn/datasets/cv_datasets /cifar.py代码是否有误? HOT 1
- som question about get_cosine_schedule_with_warmup HOT 2
- there‘s a bug in the net resnet50,the self.fc(x) is missing HOT 1
- Add Unimatch ? HOT 1
- There seems to exist a bug when using trainer class
- There is CIFAR-400 in the papaer
- Assertion on pseudolabel
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 semi-supervised-learning.