Mr.Li

把学习率改成0.001，lr_decay改成0.95.跑100个epoch ，验证集可以跑到97%左右。亲测~

@nemonameless model = 'ResNet34' # 使用的模型，名字必须与models/__init__.py中的名字一致 train_data_root = './data/train/' # 训练集存放路径 test_data_root = './data/test' # 测试集存放路径 load_model_path = './checkpoints/resnet34_0401_11:01:17.pth' # 加载预训练的模型的路径，为None代表不加载 batch_size = 128 # batch size use_gpu = True...

@nemonameless 对，跑了0.97

@qingfenghcy Permission denied: 是不是权限问题？你的checkpoints文件夹跟整个项目代码在一个目录下吗？

The same problem occurs in Python 3.8.8

> @Loovelj @Li-Lai @Klawens @bobo0810 请问你们Linux还是Mac？ linux

> The AttentionNet-IRSE pretrained model is not avaiable. And I saved the model use `torch.jit.save` api which seem like not support for finetuning. You can retrain it use this to...

> You can load the weights from torch.jit.load and set these in to the state_dict of a real model (from BACKBONE_DICT) in order to support finetuning. Oh, that's great. Can...

> > @cavalleria hello，according to data augmentation result in model_zoo.md，baseline is the best, so we do not need to do any data augmentation? > > When trained for the same...

> @xsacha @cavalleria @bobo0810 Hello, I want to find a network with a better accuracy than resnet50-IR, and it is better to have similar inference speed，could you give me some...