where is SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug/opts.yaml

[Shreyas-Bhat]

Hello, Can you help me solve this issue. I am testing the pretrained weights and this is the error i am getting

[layumi]

If you train the model, the yaml file will automatically generated in the data/outputs/your_model_name/ .

[zeroXzero]

Is it possible to share the trained model files for testing purposes?

[layumi]

Hi @zeroXzero
Thanks. I just upload my trained model, which is one of the final models we used.

• SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug (AICity 2020) can be downloaded at GoogleDrive.

[zeroXzero]

Thank you

[lhbsww]

@layumi 你好，郑博士，我在通过您提供的训练模型SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug (AICity 2020)进行测试时，会发生如下错误，请问是什么原因 Traceback（最近一次调用最后一次）： 文件“train_2020.py”，第 441 行，在 model = ft_net_SE(len(class_names), opt.droprate, opt.stride, opt.pool) 文件“/home/luhu/AIC/model .py”，第 317 行，在init model_ft = pretrainedmodels 中。dict [model_name](num_classes=1000, pretrained='imagenet') 文件“/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/pretrainedmodels/models/senet.py”，第 441 行，在 se_resnext101_32x4d initialize_pretrained_model(model, num_classes, settings) 文件“/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/pretrainedmodels/models/senet.py”，第 373 行，在 initialize_pretrained_model model.load_state_dict (model_zoo.load_url(设置['url' 文件“/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/torch/hub.py”，第 528 行，在 load_state_dict_from_url return torch.load(cached_file, map_location=map_location) 文件“/home /luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/torch/serialization.py”，第 593 行，在加载 返回 _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) 文件“/home/luhu /anaconda3/envs/one_env/lib/python3.6/site-packages/torch/serialization.py"，第 762 行，在 _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, ' <'。