ucsc-real / cifar-10-100n Goto Github PK
View Code? Open in Web Editor NEWHuman annotated noisy labels for CIFAR-10 and CIFAR-100. The website of CIFAR-N is available at http://www.noisylabels.com/.
License: Other
Human annotated noisy labels for CIFAR-10 and CIFAR-100. The website of CIFAR-N is available at http://www.noisylabels.com/.
License: Other
Hi,
I would like to load the side information and associate it with the correct sample in Tensorflow. What order do the side_info_cifar10N.csv
and side_info_cifar100N.csv
follow, the one of the PyTorch or the Tensorflow files?
And if they don't come in the Tensorflow order, should I load them like this?
import numpy as np
import pandas as pd
noise_file = np.load('./data/CIFAR-10_human_ordered.npy', allow_pickle=True)
random_label1 = noise_file.item().get('random_label1')
train_ds, test_ds = tfds.load('cifar10', split=['train','test'], as_supervised=True, batch_size = -1)
train_images, train_labels = tfds.as_numpy(train_ds)
side_info_df = pd.read_csv('side_info_cifar10N.csv')
worker1_id = df['Worker1-id'].to_numpy()
# Reorder side information with correct order
image_order = np.load('image_order_c10.npy')
worker1_id_ordered = worker1_id[image_order // 10]
# Now, the indexing of all arrays matches correctly
first_example = (train_images[0], train_labels[0], worker1_id_ordered[0])
Thank you very much!
Hello,
Can you share the individual labeling information of each labeler for CIFAR-100? (e.g., noise_file['random_label2'])
It will be great if they are provided as CIFAR-10-N.
Thank you.
For CIFAR-10N worst, the result in the paper was 77%acc by CE loss, and I only got 67%acc using your code. In addition, can you give me experimental hyperparameters related to PES (Semi). Thank you.
Dear sir, can you give me the hyperparameter setting for DivideMix on this dataset?
Hi,
I see the files below are 0 bytes.
CIFAR-100_human_ordered.npy
CIFAR-10_human_ordered.npy
I noticed this after running below from the instructions in the readme:
import numpy as np
noise_file = np.load('./data/CIFAR-100_human_ordered.npy', allow_pickle=True)
clean_label = noise_file.item().get('clean_label')
noise_label = noise_file.item().get('noise_label')
# The noisy label matches with following tensorflow dataloader
train_ds, test_ds = tfds.load('cifar100', split=['train','test'], as_supervised=True, batch_size = -1)
train_images, train_labels = tfds.as_numpy(train_ds)
# You may want to replace train_labels by CIFAR-N noisy label sets
UnpicklingError: Failed to interpret file './data/CIFAR-100_human_ordered.npy' as a pickle
Thanks
I find that the number of the coarse labels of CIFAR-100N is only 12.
My code is
import torch
noise_file = torch.load('/data/lwang/data/cifar-n/CIFAR-100_human.pt')
classes = list(set(noise_file["noisy_coarse_label"]))
class_num = len(classes)
print(classes)
print(class_num)
The output is
[1, 4, 7, 9, 10, 12, 14, 15, 16, 17, 18, 19]
12
Is there any wrong?
Dear game initiator, I noticed that the official code divides the verification set. Do we also need to divide the verification set? Can we train on the complete training set and then test on the test set?
Hello,
I'm trying to reproduce the performance of "CE" in the paper.
In "worst" label noise, the paper reports the test accuracy of 77.69 (in CIFAR-10-N).
However, when I run the provided code on my machine, the last test epoch accuracy is only 67.89 and it seems overfitting occurs to the training noisy labels.
Did you use validation set for evaluation? Or could you point out if I'm missing something?
Also, there's a discrepancy on the learning rate scheduling between the paper and code.
Learning rate decay is applied in 60th epoch in the code, but the paper says that it is applied in 50th epoch.
Could you check about it?
Thank you.
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.