python train_2020.py

[s20163081161]

@layumi 郑博士 我直接运行python train_2020.py能真确开始训练，但是按照README.md上提供的那一长传命令，就会报下面的错，这是为何？

requests.exceptions.SSLError: HTTPSConnectionPool(host='data.lip6.fr', port=443): Max retries exceeded with url: /cadene/pretrainedmodels/se_resnext101_32x4d-3b2fe3d8.pth (Caused by SSLError(SSLError("bad handshake: Error([('SSL routines', 'tls_process_server_certificate', 'certificate verify failed')],)",),))

[layumi]

应该是有墙。。下SENet 预训练模型的时候报错了

[daiguangzhao]

@layumi 郑博士 我直接运行python train_2020.py能真确开始训练，但是按照README.md上提供的那一长传命令，就会报下面的错，这是为何？

requests.exceptions.SSLError: HTTPSConnectionPool(host='data.lip6.fr', port=443): Max retries exceeded with url: /cadene/pretrainedmodels/se_resnext101_32x4d-3b2fe3d8.pth (Caused by SSLError(SSLError("bad handshake: Error([('SSL routines', 'tls_process_server_certificate', 'certificate verify failed')],)",),))

加上以下代码，原因你自己ＣＳＤＮ哈：
import ssl

ssl._create_default_https_context = ssl._create_unverified_context

[daiguangzhao]

郑博士，你好，请问
name SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug，这个对应哪一块代码，论文哪里提到了？麻烦，谢谢

[s20163081161]

@layumi 郑博士 我直接运行python train_2020.py能真确开始训练，但是按照README.md上提供的那一长传命令，就会报下面的错，这是为何？
requests.exceptions.SSLError: HTTPSConnectionPool(host='data.lip6.fr', port=443): Max retries exceeded with url: /cadene/pretrainedmodels/se_resnext101_32x4d-3b2fe3d8.pth (Caused by SSLError(SSLError("bad handshake: Error([('SSL routines', 'tls_process_server_certificate', 'certificate verify failed')],)",),))

加上以下代码，原因你自己ＣＳＤＮ哈：
import ssl

ssl._create_default_https_context = ssl._create_unverified_context

我直接翻墙下载了

[HanwenCao]

郑博士，你好，请问
name SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug，这个对应哪一块代码，论文哪里提到了？麻烦，谢谢

请问您知道了吗？

[layumi]

@HanwenCao
这就是 SENet的basic model，跑的时候起的名字。

[lhbsww]

Traceback (most recent call last):
File "train_2020.py", line 441, in
model = ft_net_SE(len(class_names), opt.droprate, opt.stride, opt.pool)
File "/home/luhu/AIC/model.py", line 317, in init
model_ft = pretrainedmodels.dict[model_name](num_classes=1000, pretrained='imagenet')
File "/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/pretrainedmodels/models/senet.py", line 441, in se_resnext101_32x4d
initialize_pretrained_model(model, num_classes, settings)
File "/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/pretrainedmodels/models/senet.py", line 373, in initialize_pretrained_model
model.load_state_dict(model_zoo.load_url(settings['url']))
File "/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/torch/hub.py", line 528, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location)
File "/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/torch/serialization.py", line 593, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/home/luhu/anaconda3/envs/one_env/lib/python3.6/site-packages/torch/serialization.py", line 762, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '<'.

请问在执行train_2020.py时，出现这个错误是什么原因，要怎么解决