use default_generator.seed() as random_seed in init

[daquexian]

修复没有设置 random_seed 导致的多次运行 tensor.normal_() 等随机初始化方法得到的数据一样的问题

[github-actions]

CI failed, removing label automerge

[github-actions]

CI failed, removing label automerge

[github-actions]

Speed stats:

GPU Name: GeForce GTX 1080 

PyTorch resnet50 time: 141.2ms (= 7062.0ms / 50, input_shape=[16, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 128.5ms (= 6422.7ms / 50, input_shape=[16, 3, 224, 224], backward is enabled)
Relative speed: 1.10 (= 141.2ms / 128.5ms)

PyTorch resnet50 time: 83.8ms (= 4192.3ms / 50, input_shape=[8, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 74.3ms (= 3717.3ms / 50, input_shape=[8, 3, 224, 224], backward is enabled)
Relative speed: 1.13 (= 83.8ms / 74.3ms)

PyTorch resnet50 time: 54.6ms (= 2732.1ms / 50, input_shape=[4, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 49.6ms (= 2482.1ms / 50, input_shape=[4, 3, 224, 224], backward is enabled)
Relative speed: 1.10 (= 54.6ms / 49.6ms)

PyTorch resnet50 time: 49.0ms (= 2447.9ms / 50, input_shape=[2, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 40.7ms (= 2034.5ms / 50, input_shape=[2, 3, 224, 224], backward is enabled)
Relative speed: 1.20 (= 49.0ms / 40.7ms)

PyTorch resnet50 time: 42.6ms (= 2130.4ms / 50, input_shape=[1, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 41.5ms (= 2076.2ms / 50, input_shape=[1, 3, 224, 224], backward is enabled)
Relative speed: 1.03 (= 42.6ms / 41.5ms)