chyelang / hw2_image_classification
利用TensorFlow（TF），本作业实现了一个基于full convolution stack、inception v2 module等模块的图片分类网络，纵向共包含10层包含参数的层，采用自己搭建的卷积层。对于dset1与dset2采用同样的网络结构，分别进行训练。最终在dset1验证集（约含900张图，下同）上的Top1分类准确率约为0.52，在dset2验证集上的Top1准确率约为0.63。在K80显卡的单核上，该模型的训练速度约为205张图每秒，最终所得模型的checkpoint约为45MB。
☆12Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for hw2_image_classification
- some small codes about deep learning☆51Updated 6 years ago
- keras融合inception,vgg,residual_net做一个超快的迁移学习模型☆11Updated 6 years ago
- ☆47Updated 7 years ago
- ☆65Updated 6 years ago
- 一个面向初学者的，友好的Keras入门教程☆123Updated 5 years ago
- a baseline for baidu dog classification competition.☆113Updated 6 years ago
- tensorflow->BCNN + pytorch -> vgg16/resnet/BCNN☆92Updated 5 years ago
- common data structures and algorithms in Python☆67Updated 4 years ago
- TensorFlow的练习代码☆44Updated 6 years ago
- data augmentation on python☆35Updated 6 years ago
- 天池比赛，kaggle等等（Keras/PyTorch实战）☆181Updated 4 years ago
- 深度学习入门的一些简单例子☆353Updated 5 years ago
- mutil-class focal loss implemented in keras☆159Updated 5 years ago
- The code on deep learning.☆74Updated 6 years ago
- 京东 JDD 大赛 猪脸识别项目☆76Updated 5 years ago
- 谷歌INCEPTION-RESNET-V2迁移学习实现图像二分类判断图像是否生病☆17Updated 6 years ago
- some real example of machine learn algorithm☆65Updated 3 years ago
- Models built with TensorFlow☆34Updated 7 years ago
- 使用 TensorFlow 进行 finetuning 的通用分类模型☆85Updated 6 years ago
- cnn+rnn: vgg(vgg16,vgg19)+rnn(LSTM, GRU), resnet(resnet_v2_50,resnet_v2_101,resnet_v2_152)+rnnrnn(LSTM, GRU), inception_v4+rnn(LSTM, GRU)…☆64Updated 6 years ago
- Deep learning algorithms source code for beginners with python3☆28Updated 5 years ago
- 使用keras版本的Mask-RCNN来训练自己的数据，通过代码把样本制作麻烦的步骤变成简单方便。☆49Updated 6 years ago
- 2018广东工业智造大数据创新大赛——智能算法赛☆35Updated 6 years ago
- share examples of tensorflow☆63Updated 6 years ago
- 我的深度学习历程☆49Updated 3 years ago
- ☆82Updated 6 years ago
- TensorFlow实现Kaggle猫狗大战☆57Updated 7 years ago
- ☆120Updated 8 years ago
- 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☆58Updated 5 years ago