XianxinMao的博客

嵌入模型是一种将非结构化数据（如文本、图像和音频）转换为数值形式（即向量或嵌入）的方法。这些数值表示能够捕捉数据中的语义和结构信息，使得相似内容的嵌入在高维空间中距离接近，而不相关的内容则距离较远。具体来说，在自然语言处理（NLP）中，嵌入模型会将单词、句子或段落转换为固定长度的向量。例如，词嵌入技术（如Word2Vec、GloVe）可以将单词转换为向量，使得“王子”与“公主”的向量距离较近，而“王子”与“汽车”的向量距离则较远。

优化的注意力机制与新的数据提取方式相结合，通过减少计算复杂度、内存占用和训练时间，提高了Transformer模型在处理可变长度输入序列时的整体性能。这不仅可以降低AI模型的运行成本，还能为实际应用提供更快速、高效的解决方案。

Introducing_TensorFlow_Graph_Neural_NetworksToday, we are excited to release TensorFlow Graph Neural Networks (GNNs), a library designed to make it easy to work with graph structured data using TensorFlow.Graphs are all around us, in the real world and i

Basic_regression_Predict_fuel_efficiencyIn a regression problem, the aim is to predict the output of a continuous value, like a price or a probability. Contrast this with a classification problem, where the aim is to select a class from a list of classes

Tensorflow_Similarity_Supervised_Learning_Hello_WorldThis notebook demonstrates how to use TensorFlow Similarity to train a SimilarityModel() on a fraction of the MNIST classes, and yet the model is able to index and retrieve similar looking images for al

tensorflow_similarityToday we are releasing the first version of TensorFlow Similarity, a python package designed to make it easy and fast to train similarity models using TensorFlow.Examples of nearest neighbor searches performed on the embeddings gene

text_classification文本分类对 IMDB 数据集里的评论进行情感分析，其实就是分为正面和负面两类评论对 Stack Overflow 上的编程问题进行打标签This tutorial demonstrates text classification starting from plain text files stored on disk. You’ll train a binary classifier to perform sentiment analysis on an IM

我们这里处理的是 CSV 数据There are two main parts to this:Loading the data off diskPre-processing it into a form suitable for training.This tutorial focuses on the loading, and gives some quick examples of preprocessing. For a tutorial that focuses on the prep

1.数据读取，然后对数据进行预处理，把 x 转化成 float-point，y 还是保留 label 形式2.搭建模型，要指定输入的 input_shape3.compile 里面要指定 optimizer，loss_function，metric4.对模型进行评估，预测的输出要经过 softmax 得到 probability 形式的表示唯一有特点的地方是对预测的输出做了可视化处理This guide uses the Fashion MNIST dataset which contains 7

import tensorflow as tfprint("TensorFlow version:", tf.__version__)mnist = tf.keras.datasets.mnist(x_train, y_train), (x_test, y_test) = mnist.load_data()x_train, x_test = x_train / 255.0, x_test / 255.0model = tf.keras.models.Sequential([ tf.

Pytorchtorchstattorchstat: The Pytorch Model AnalyzerThis is a lightweight neural network analyzer based on Pytorch. It is designed to make building your networks quick and easy, with the ability to debug them.This tools can show:Total number of netw

cord_19_embeddings_kerasThese embeddings were trained on the titles, authors, abstracts, body texts, and reference titles of articles in the CORD-19 datasetIn this colab we will:Analyze semantically similar words in the embedding spaceTrain a classifi

bangla_article_classifierThis Colab is a demonstration of using TensorFlow Hub for text classification in non-English/local languages. Here we choose Bangla as the local language and use pretrained word embeddings to solve a multiclass classification task

text_classification_with_tf_hub_on_kaggleTF-Hub is a platform to share machine learning expertise packaged in reusable resources, notably pre-trained modules. In this tutorial, we will use a TF-Hub text embedding module to train a simple sentiment classif

semantic_similarity_with_tf_hub_universal_encoderThis notebook illustrates how to access the Universal Sentence Encoder and use it for sentence similarity and sentence classification tasksThe Universal Sentence Encoder makes getting sentence level embedd

bert_glueBERT can be used to solve many problems in natural language processing. You will learn how to fine-tune BERT for many tasks from the GLUE benchmark:CoLA (Corpus of Linguistic Acceptability): Is the sentence grammatically correct ?SST-2 (Stanfo

bert_expertsThis colab demonstrates how to:Load BERT models from TensorFlow Hub that have been trained on different tasks including MNLI, SQuAD, and PubMedUse a matching preprocessing model to tokenize raw text and convert it to idsGenerate the pooled

retrieval_with_tf_hub_universal_encoder_qaThis is a demo for using Universal Encoder Multilingual Q&A model for question-answer retrieval of text, illustrating the use of question_encoder and response_encoder of the model. We use sentences from SQuAD

tf2_semantic_approximate_nearest_neighborsThis tutotial illustrates how to generate embeddings from a TensorFlow Hub (TF-Hub) module given input data, and build an approximate nearest neighbours (ANN) index using the extracted embeddings. The index can th

classify_text_with_bertThis tutorial contains complete code to fine-tune BERT to perform sentiment analysis on a dataset of plain-text IMDB movie reviews. In addition to training a model, you will learn how to preprocess text into an appropriate format.I

tf2_text_classificationThis notebook classifies movie reviews as positive or negative using the text of the review. This is an example of binary or two-class-classification, an important and widely applicable kind of machine learning problemWe’ll use the

image_enhancingThis colab demonstrates use of TensorFlow Hub Module for Enhanced Super Resolution Generative Adversarial Network for image enhancingModel trained on DIV2K Dataset (on bicubically downsampled images) on image patches of size 128 x 128impo

boundlessBoundless is a model for image extrapolation. This model takes an image, internally masks a portion of it (1/2, 1/4, 3/4) and completes the masked part. For more details refer to Boundless: Generative Adversarial Networks for Image Extension or t

cropnet_on_deviceThis notebook shows you how to fine-tune CropNet models from TensorFlow Hub on a dataset from TFDS or your own crop disease detection dataset.You will:Load the TFDS cassava dataset or your own dataEnrich the data with unknown (negativ

cropnet_cassavaThis notebook shows how to use the CropNet cassava disease classifier model from Tensorflow Hub. The model classifies images of cassava leaves into one of 6 classes: bacterial blight, brown streak disease, green mite, mosaic disease, health

tf_hub_generative_image_moduleThis Colab demonstrates use of a TF-Hub module based on a generative adversarial network (GAN). The module maps from N-dimensional vectors, called latent space, to RGB imagesTwo examples are provided:Mapping from latent sp

tf2_object_detectionTo visualize the images with the proper detected boxes, keypoints and segmentation, we will use the TensorFlow Object Detection APILoad label map data (for plotting):Label maps correspond index numbers to category names, so that when

tf2_arbitrary_image_stylizationBased on the model code in magenta and the publication:Exploring the structure of a real-time, arbitrary neural artistic stylization networkimport functoolsimport osimport timefrom matplotlib import gridspecimport matp

tf2_image_retrainingImage classification models have millions of parameters. Training them from scratch requires a lot of labeled training data and a lot of computing power. Transfer learning is a technique that shortcuts much of this by taking a piece of

image_classificationBecause TF Hub encourages a consistent input convention for models that operate on images, it’s easy to experiment with different architectures to find the one that best fits your needsThere are some technical differences between the

text_to_video_retrieval_with_s3d_milnceThis tutorial demonstrates how to use the S3D MIL-NCE model from Tensorflow Hub to do text-to-video retrieval to find the most similar videos for a given text query.The model has 2 signatures, one for generating vid

video_inbetweening_conv3dFrom Here to There: Video Inbetweening Using Direct 3D Convolutions, 2019Current Hub characteristics:has models for BAIR Robot pushing videos and KTH action video dataset (though this colab uses only BAIR)BAIR dataset already

action_recognition_with_tf_hubrecognizing actions in video data using the tfhub.dev/deepmind/i3d-kinetics-400/1 moduleMore models to detect actions in videos can be found here解读: 用 tfhub.dev/deepmind/i3d-kinetics-400/1 模块去识别视频数据里的动作The underlying model

tflite_pose_classificationThis notebook teaches you how to train a pose classification model using MoveNet and TensorFlow Lite. The result is a new TensorFlow Lite model that accepts the output from the MoveNet model as its input, and outputs a pose class

tflite_object_detectionThe Model Maker library uses transfer learning to simplify the process of training a TensorFlow Lite model using a custom dataset. Retraining a TensorFlow Lite model with your own custom dataset reduces the amount of training data r

TFLite_tutorialsThe TensorFlow Lite Model Maker library simplifies the process of adapting and converting a TensorFlow neural-network model to particular input data when deploying this model for on-device ML applications.解读: 此处我们想要得到的是 .tflite 格式的模型，用于在移

tensorflow lite model makermetadata which provides a standard for model descriptionsThe default model is EfficientNet-Lite0.Currently, we support several models such as EfficientNet-Lite* models, MobileNetV2, ResNet50 as pre-trained models for image cla

TensorFlow Litehttps://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/examples/python/TensorFlow Lite Python image classification demo# Get photocurl https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/lite/examples/

How to implement an OCR model using CNNs, RNNs, and CTC loss.This example demonstrates a simple OCR model built with the Functional API. Apart from combining CNN and RNN, it also illustrates how you can instantiate a new layer and use it as an “Endpoint l

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