AI+无线通信总结——初赛算法实现(Top37)

先上代码。剩下的有时间在补,最终提交的初赛排名是37,但是没有跑完,跑完应该能进前20,但是由于算力不足,只跑了50个epoch。我先抛个砖,希望能引来玉。

完整代码:

Model_define_pytorch.py

#!/usr/bin/env python3
"""An Implement of an autoencoder with pytorch.
This is the template code for 2020 NIAC https://naic.pcl.ac.cn/.
The code is based on the sample code with tensorflow for 2020 NIAC and it can only run with GPUS.
If you have any questions, please contact me with https://github.com/xufana7/AutoEncoder-with-pytorch
Author, Fan xu Aug 2020

changed by seefun Aug 2020 
github.com/seefun | kaggle.com/seefun
"""
import numpy as np
import torch.nn as nn
import torch
import torch.nn.functional as F
from torch.utils.data import Dataset
from collections import OrderedDict

channelNum = 64


class Mish(torch.nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):
        x = x * (torch.tanh(torch.n

你可能感兴趣的:(人工智能,pytorch,深度学习,机器学习,神经网络)