In this paper, we propose a frequency-time division network (FreqTimeNet) to improve the performance of deep learning (DL) based OFDM channel estimation. This FreqTimeNet is designed based on the orthogonality between the frequency domain and the time domain. In FreqTimeNet, the input is processed by parallel frequency blocks and parallel time blocks in sequential. Introducing the attention mechanism to use the SNR information, an attention based FreqTimeNet (AttenFreqTimeNet) is proposed. Using 3rd Generation Partnership Project (3GPP) channel models, the mean square error (MSE) performance of FreqTimeNet and AttenFreqTimeNet under different scenarios is evaluated. A method for constructing mixed training data is proposed, which could address the generalization problem in DL. It is observed that AttenFreqTimeNet outperforms FreqTimeNet, and FreqTimeNet outperforms other DL networks, with acceptable complexity.

翻译：在本文中,我们提议建立一个基于 OFDM 频道估计的频率分流网络(FreqTimeNet), 以改善深学习(DL) 的性能。 这个 FreeqtimeNet 是根据频率域与时间域之间的正方形设计。 在 FreeqTimeNet 中, 输入由平行频率区块和相继的平行时区块处理。 在引入关注机制以使用 SNR 信息时, 提议建立一个基于关注的 FreeqtimeNet (AttenFreqTimeNet ) 。 使用第三代伙伴关系项目( 3GPP) 频道模型, FreqidTimeNet 和 AttenFreqTimeNet 在不同情景下的平均方形错误( MSE ) 的性能得到了评估。 提出了构建混合培训数据的方法, 这种方法可以解决 DL 的通用问题 。 观察到 AtenFreqTimeNet Net 超过 FrecTimeNet 和 FredeTimeNet 其它 DL 网络, 复杂程度可以接受。