EfficientNet论文

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is unknown. The combination of these methods with the Long Short-term Memory RNN architecture has proved particularly fruitful, delivering state-of-the-art results in cursive handwriting recognition. However RNN performance in speech recognition has so far been disappointing, with better results returned by deep feedforward networks. This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs. When trained end-to-end with suitable regularisation, we find that deep Long Short-term Memory RNNs achieve a test set error of 17.7% on the TIMIT phoneme recognition benchmark, which to our knowledge is the best recorded score.

循环神经网络在语音识别中的应用 LSTM 双向RNN 双向lstm

Michael Nielsen大神的巨作NNDL中文版，对深度学习基础讲解非常透彻

这是复现论文Learning to Compare Image Patches via Convolutional Neural Networks的代码，这是TensorFlow版本，用深度学习的方法做图像匹配，具体的过程可以看这篇文章https://blog.csdn.net/weixin_42521239/article/details/103389033

Context-Dependent Pre-trained Deep Neural Networks for Large Vocabulary Speech Recognition

involution.pytorch（） 一个PyTorch实现使用过密的 对合的非官方pytorch实现。 官方实现可以在找到。 特征 该层可以处理任意输入和输出通道，内核大小，步幅和减速比。 但是，输入通道应按组划分。 要求 pytorch >= 1.4.0 einops >= 0.3.0 用法 一个例子： >>> import torch >>> from involution import Involution >>> >>> x = torch.rand(2,8,5,5) >>> i = Involution(in_channels=8, out_channels=4, groups=4, kernel_size=3, stride=2, reduction_ratio=2) >>> i(x).size () torch.Size([2, 4, 3, 3]) 去做 Ima

edit by ripley. university oxford

ResneXt网络论文

在PyTorch中检索CNN图像：在PyTorch中训练和评估CNN以进行图像检索 这是一个Python工具箱，用于实现对本文所述方法的培训和测试： 无需人工注释即可对CNN图像进行微调， RadenovićF.，Tolias G.，Chum O.，TPAMI 2018 [ ] CNN图像检索从BoW获悉：无监督的微调，并附有困难的示例， RadenovićF.，Tolias G.，Chum O.，ECCV 2016 [ ] 它是什么？ 该代码实现： 训练（微调）CNN进行图像检索 学习CNN图像表示的监督美白 在牛津和巴黎数据集上测试CNN图像检索 先决条件 为了运行此工具箱，您将需要： Python3（在Debian 8.1上使用Python 3.7.0进行了测试） PyTorch深度学习框架（已通过1.0.0版测试） 其余所有（数据+网络）将通过我们的脚本自动下载