have upgraded pretrained models to pytorch1.x

https://github.com/HuaizhengZhang/scene-recognition-pytorch1.x-tf2.x

I have retrained many models by using pytorch 1.4 based on python3.7.

Anyone interested in using scene classification models with the latest pytorch version is free to access.

The project is still under active development. You are welcome to PR.
```
PyTorch version: 1.4.0
Is debug build: No
CUDA used to build PyTorch: 10.1

OS: Ubuntu 18.04.3 LTS
GCC version: (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0
CMake version: version 3.10.2

Python version: 3.7
Is CUDA available: Yes
CUDA runtime version: 10.1.243

Nvidia driver version: 418.116.00
cuDNN version: /usr/lib/x86_64-linux-gnu/libcudnn.so.7.6.2

Versions of relevant libraries:
[pip] numpy==1.18.1
[pip] torch==1.4.0
[pip] torchvision==0.5.0
```