-
**Describe the bug**
When I use your train.py script, I struggle with Error messages with data/cutmix.py:
1. RuntimeError: Caught RuntimeError in DataLoader worker process 0
2. RuntimeError: Ind…
-
Hey,
I've been finetuning ViT on different datasets (cifar100, oxford_pets, etc.). I am using Google TRC TPUs, specifically V3 VM using the bits_and_tpu branch. I have found the results of finetuning…
-
- [Cifar-100とResNet18を用いてデータ拡張手法を比較してみた。](https://blog.tan5o.com/2020/07/cifar-100%E3%81%A8resnet18%E3%82%92%E7%94%A8%E3%81%84%E3%81%A6%E3%83%87%E3%83%BC%E3%82%BF%E6%8B%A1%E5%BC%B5%E6%89%8B%E6%B3%95%E…
-
## 🚀 Feature
Need [RandAugment](https://arxiv.org/pdf/1909.13719.pdf) module inside `torchvision.transforms` for augmenting images before training. This would ease the implementation of RandAugment…
-
I manage cityscapes data dir structure as Prepare data in readme. But, raise an error of not find the file.
I find that file path has been changed in BaseDataset, it add "gtFine_labelTrainIds.png" in…
-
Be sure you've searched [the forums](https://forums.fast.ai) for the error message you received. Also, unless you're an experienced fastai developer, first ask on the forums to see if someone else has…
-
This is for three class.
If I want to design a target with [0.8 0.15 0.05].
How can I do ?
https://github.com/rwightman/pytorch-image-models/blob/f83b0b01e3a28f0408431e8e88acda641d22f299/timm/loss/…
-
Hello! I try to reproduce your model,but when I evaluate the pretrained model(BossNet-T0-80_8.pth),the ACC1 is too low! Did i miss something? Can you help me?
The run command as follows:
root@…
-
I have been advised by @fchollet to open the proposed solution in `keras-cv` instead of `keras`.
The problem when training a neural networ using [TripletLoss](https://github.com/tensorflow/addons/b…
-
I am getting this error:
Namespace(aa='rand-m9-mstd0.5-inc1', batch_size=64, clip_grad=None, color_jitter=0.4, cooldown_epochs=10, cutmix=1.0, cutmix_minmax=None, data_path='/content/stonks', data_se…