-
First of all, thanks for publishing the code for this paper -- it makes reproducing your work much easier.
I am trying to run fixmatch with RandAugment+Cutout instead of CTAugment (as it's much eas…
-
Hi,
I just realized that links to source code are broken in the docs.
Best!
-
Are we interested in https://github.com/google-research/simclr/blob/master/data_util.py?
bhack updated
4 years ago
-
I'm working on a medical imaging dataset and have previously tried the `torchvision` weights of resnet50 for fine-tuning. Changing those weights with the one provided in this library (79.038) has show…
-
```
from PIL import Image
import imgaug.augmenters as iaa
import numpy as np
import matplotlib.pyplot as plt
img_fpath = "img.png"
with Image.open(img_fpath) as f:
in_image = f.convert('R…
-
arxiv link of paper "RandAugment: Practical automated data augmentation with a reduced search space" is wrong, which should be [https://arxiv.org/pdf/1909.13719.pdf](https://arxiv.org/pdf/1909.13719.p…
-
```python
import argparse
import os
import sys
import time
import torch
from apex import amp
from runx.logx import logx
from config import assert_and_infer_cfg, update_epoch, cfg
from utils…
-
I tried to use RandAugment as well as the RandErasing augmentation but whenever I start the training I get the error: "EOFError: Ran out of input"
Full output follows:
```
=======================…
-
利用训练房子方向的算法 训练整图的0 90 180 270 的方向 训练过程中还好好的 有acc 但是最后best metirc acc 不知道为什么是0 请教各位大佬
[2021/03/20 11:41:57] root INFO: Architecture :
[2021/03/20 11:41:57] root INFO: Backbone :
[2021/…
-
Hi. Thanks for this amazing work.
I have a question though. Is there a specific reason for which you choose the augmentations Jitter, Grayscale and Gaussian Blur? Do you know if stronger augmentati…