All Projects → Hellcatzm → TransforLearning_TensorFlow

Hellcatzm / TransforLearning_TensorFlow

Licence: other
使用预训练好的InceptionV3模型对自己的数据进行分类,用这个代码的同学希望可以给一个star

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to TransforLearning TensorFlow

Deep-Learning
It contains the coursework and the practice I have done while learning Deep Learning.🚀 👨‍💻💥 🚩🌈
Stars: ✭ 21 (-63.79%)
Mutual labels:  transfer-learning, inceptionv3
DeepFaceRecognition
Face Recognition with Transfer Learning
Stars: ✭ 16 (-72.41%)
Mutual labels:  transfer-learning, inceptionv3
Skin Lesions Classification DCNNs
Transfer Learning with DCNNs (DenseNet, Inception V3, Inception-ResNet V2, VGG16) for skin lesions classification
Stars: ✭ 47 (-18.97%)
Mutual labels:  transfer-learning, inceptionv3
nlp workshop odsc europe20
Extensive tutorials for the Advanced NLP Workshop in Open Data Science Conference Europe 2020. We will leverage machine learning, deep learning and deep transfer learning to learn and solve popular tasks using NLP including NER, Classification, Recommendation \ Information Retrieval, Summarization, Classification, Language Translation, Q&A and T…
Stars: ✭ 127 (+118.97%)
Mutual labels:  transfer-learning
brand-sentiment-analysis
Scripts utilizing Heartex platform to build brand sentiment analysis from the news
Stars: ✭ 21 (-63.79%)
Mutual labels:  transfer-learning
backprop
Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
Stars: ✭ 229 (+294.83%)
Mutual labels:  transfer-learning
self-driving-car
Implementation of the paper "End to End Learning for Self-Driving Cars"
Stars: ✭ 54 (-6.9%)
Mutual labels:  transfer-learning
sparsezoo
Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
Stars: ✭ 264 (+355.17%)
Mutual labels:  transfer-learning
awesome-graph-self-supervised-learning
Awesome Graph Self-Supervised Learning
Stars: ✭ 805 (+1287.93%)
Mutual labels:  transfer-learning
ATA-GAN
Demo code for Attention-Aware Generative Adversarial Networks paper
Stars: ✭ 13 (-77.59%)
Mutual labels:  transfer-learning
Transformers-Domain-Adaptation
Adapt Transformer-based language models to new text domains
Stars: ✭ 67 (+15.52%)
Mutual labels:  transfer-learning
oreilly-bert-nlp
This repository contains code for the O'Reilly Live Online Training for BERT
Stars: ✭ 19 (-67.24%)
Mutual labels:  transfer-learning
smoke-detection-transfer-learning
use transfer learning to detect smoke in images and videos
Stars: ✭ 16 (-72.41%)
Mutual labels:  transfer-learning
neuro-evolution
A project on improving Neural Networks performance by using Genetic Algorithms.
Stars: ✭ 25 (-56.9%)
Mutual labels:  transfer-learning
wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
Stars: ✭ 39 (-32.76%)
Mutual labels:  transfer-learning
Land-Cover-Classification-using-Sentinel-2-Dataset
Application of deep learning on Satellite Imagery of Sentinel-2 satellite that move around the earth from June, 2015. This image patches can be trained and classified using transfer learning techniques.
Stars: ✭ 36 (-37.93%)
Mutual labels:  transfer-learning
object detection
Implementatoin of object detection using Tensorflow 2.1.0 | this can be use in a car for object detection
Stars: ✭ 13 (-77.59%)
Mutual labels:  transfer-learning
BA3US
code for our ECCV 2020 paper "A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation"
Stars: ✭ 31 (-46.55%)
Mutual labels:  transfer-learning
ProteinLM
Protein Language Model
Stars: ✭ 76 (+31.03%)
Mutual labels:  transfer-learning
histopathologic cancer detector
CNN histopathologic tumor identifier.
Stars: ✭ 26 (-55.17%)
Mutual labels:  transfer-learning

迁移学习TransforLearning

『TensorFlow』迁移学习

1、相关下载

数据和预训练模型下载:

curl -O http://download.tensorflow.org/example_images/flower_photos.tgz
wget https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip

2、项目简介

本项目将使用ImageNet数据集预训练好的InceptionV3网络结构舍弃后面全连接层,使用了新的分类器对花朵数据进行了迁移学习,迁移学习对于这种中等偏小的数据集又为合适。

项目文件


inception_dec_2015:模型存放文件夹,下载后解压模型文件就会生成
flower_photos:文件目录,下面包含各个子类的文件夹,如果使用自己的数据的话,将自己数据各个类别分别放入一个文件夹,文件夹名字是类的字符串名字即可,将这些文件夹放入flower_photos文件夹内即可
TransforLearning.py:主程序,用于训练,不过注意,可训练文件格式应该是jpg(jpeg、JPG等等写法均可)
TransferLearning_reload.py:用于预测,仅能进行单张图片类别预测,需要进入文件中(21行左右),将image_path修改为自己的图片路径
其他文件夹为程序自己生成,不需要提前新建
文件夹Keras_TransforLearning MXnet_TransforLearning 分别展示了使用Keras和MXNet快速进行分类任务的接口调用Demo,由于使用的是高级API,可以极快上手,值得学习

运行命令

首先训练,

python TransforLearning.py

等待训练完成后(不等也行,不过需要保证已经有训练中间生成模型被保存了),预测一张自己的图片,

python TransferLearning_reload.py

命令很简单,之后就会输出预测信息,如下格式,
第一行表示分类的类别,这里是根据图片文件夹的名字来的,可以看到和之前的项目文件示意图中flower_photos的子文件夹名称一一对应;第二行为分类结果,每一个值和第一行对应位置的类别相对应,比如这个结果就是分类为daisy的概率为0.23

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].