gogo03
gogo03
> Im training my own data set using 'train_CoarseNet.ipynb' on google colab. But the sessions gets crashed before final computation. How can I resolve this. hi,ud38,could u share your dataset...
when I use the following command line. the error is disappeared. python search.py -c confs/wresnet40x2_cifar10_b512.yaml --cv_ratio 0.1
I found the following codes in search.py is the key: for epoch in tqdm_epoch: while True: epochs = OrderedDict() for exp_idx in range(num_experiments): try: if os.path.exists(default_path[exp_idx]): latest_ckpt = torch.load(default_path[exp_idx]) epochs['default_exp%d'...
excellent work! thank you, I have test Cutout using Pytorch and wide-resnet without OctConv,also don't use cutout method.the accuracy of Cifar100 is about 81.5%。 here is the website: https://github.com/uoguelph-mlrg/Cutout/blob/master/train.py Could...
I have not tried another ways. Octconv maybe not a effective method,but it can open our mind. if i have time,I'll try the dataset of imagenet-1k ,Perhaps the size of...
because octconv has low Convs,it may loss a lot of features compares with high conv.
Hi,koshian2: I have tried the dataset of imagenet_3(imagenet_10) which selected 3 or 10 categories from imagenet-1k),the input shape is (112,112,3) batch is 8,I found octconv is better than normal on...
楼上的，加一下V或邮件: [email protected] 多沟通，我刚好也在搞这一块。
楼上的，是怎么清除代理？谢谢。
确实，好像连上vpn就不行了。