XianxinMao的博客

目前我认为在分类领域上，最有研究价值的是 ResNet、Transformer。一个是从 Papers with code 的 benchmark 判断，另外一个是对以往 DenseNet、Inception 等网络的实验。深度学习从 2012 年的 AlexNet 开始，然后是 VGG，网络是往更深的方向发展，直到遇到一个问题，网络越深，模型性能开始下降。在排除了梯度消失/爆炸以及过拟合问题之后，发现是网络的优化困难问题。这时候提出的 Residual Learning，也就是 ResNet 解决了该问题

首先把数据集的情况放上来，如下图所示:然后再看一下要用到的一些组件，如下图所示:最后一起看下模型的训练流程:最后一起看下训练的结果日志，如下图所示，可以看到 testAcc = 93.86%，此处用的是双卡 2080Ti，比单卡来说，训练的 batch_size 更大，所以准确率略微提升:还有一些地方可以总结下:模型在训练过程当中的指标有 loss 和 accuracy，从长期来看 loss 呈下降趋势，accuracy 呈上升趋势为了加快训练速度，可以在训练过程中不计算 train_a

In this tutorial, you will learn how to augment your network using a visual attention mechanism called spatial transformer networks.Spatial transformer networks are a generalization of differentiable attention to any spatial transformation. Spatial trans

我自己写的代码和该教程略有不一样，有三处改动，第一个地方是用归一化(均值为0，方差为1)代替数值缩放([0, 1])，代替的理由是能提升准确率第二处改动是添加了正则化，在Conv2D和Dense Layer中均有添加，可以抑制模型过拟合，提升val_acc第三处改动是对模型训练五次进行acc取平均值，因为keras训练模型会有准确率波动，详细代码见文末链接This tutorial demonstrates training a simple Convolutional Neural Netwo

本次教程的目的是带领大家学会基本的花朵图像分类首先我们来介绍下数据集，该数据集有5种花，一共有3670张图片，分别是daisy、dandelion、roses、sunflowers、tulips，数据存放结构如下所示我们可以展示下roses的几张图片接下来我们需要加载数据集，然后对数据集进行划分，最后形成训练集、验证集、测试集，注意此处的验证集是从训练集切分出来的，比例是8:2对数据进行探索的时候，我们发现原始的像素值是0-255，为了模型训练更稳定以及更容易收敛，我们需要标准化数据

This tutorial shows how to load and preprocess an image dataset in three ways. First, you will use high-level Keras preprocessing utilities and layers to read a directory of images on disk. Next, you will write your own input pipeline from scratch using tf

Import TensorFlow into your program:import tensorflow as tf​from tensorflow.keras.layers import Dense, Flatten, Conv2Dfrom tensorflow.keras import ModelLoad and prepare the MNIST dataset.mnist = tf.keras.datasets.mnist​(x_train, y_train), (x_t

This short introduction uses Keras to: Build a neural network that classifies images. Train this neural network. And, finally, evaluate the accuracy of the model. import tensorflow as tfLoad and prepare the MNIST dataset. Convert the samp

This guide trains a neural network model to classify images of clothing, like sneakers and shirts.This guide uses tf.keras, a high-level API to build and train models in TensorFlow.# TensorFlow and tf.kerasimport tensorflow as tf​# Helper libraries

本次教程的目的是带领大家学会用 Tensorflow serving 部署训练好的模型这里我们用到的数据集是 Fashion MNIST，所以训练出来的模型可以实现以下几个类别的分类'T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'因为这篇教程主要关注部署，所以我们直接从已经训练好的模型开始，保存的格式是...

In contrast to previous region-based detectors such as Fast/Faster R-CNN [6, 18] that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almo...

Fast R-CNN achieves near real-time rates using very deep networks, when ignoring the time spent on region proposals. Now, proposals are the test-time computational bottleneck in state-of-the-art detec...

link address: https://realpython.com/blog/python/face-detection-in-python-using-a-webcam/import cv2import sysimport logging as logimport datetime as dtfrom time import sleepcascPath = "haarcasca...

link address: https://realpython.com/blog/python/face-recognition-with-python/OpenCV is the most popular library for computer vision. Originally written in C/C++, it now provides bindings for PythonOp...