经典 CNNs 的 TensorFlow 实现资源汇总

本文简单整理了网上公布的基于 TensorFlow 实现图像语义分析的一些经典网络,方便大家参考学习。


1. TensorFlow-Slim

TF-Slim 是 tensorflow 较新版本的扩充包,可以简化繁杂的网络定义,其中也提供了一些demo:

  • AlexNet
  • InceptionV1/V2/V3
  • OverFeat
  • ResNet
  • VGG

例如 VGG-16 网络,寥寥数行就可以定义完毕:

def vgg16(inputs):
  with slim.arg_scope([slim.conv2d, slim.fully_connected],
                      activation_fn=tf.nn.relu,
                      weights_initializer=tf.truncated_normal_initializer(0.0, 0.01),
                      weights_regularizer=slim.l2_regularizer(0.0005)):
    net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
    net = slim.max_pool2d(net, [2, 2], scope='pool1')
    net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
    net = slim.max_pool2d(net, [2, 2], scope='pool2')
    net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
    net = slim.max_pool2d(net, [2, 2], scope='pool3')
    net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
    net = slim.max_pool2d(net, [2, 2], scope='pool4')
    net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
    net = slim.max_pool2d(net, [2, 2], scope='pool5')
    net = slim.fully_connected(net, 4096, scope='fc6')
    net = slim.dropout(net, 0.5, scope='dropout6')
    net = slim.fully_connected(net, 4096, scope='fc7')
    net = slim.dropout(net, 0.5, scope='dropout7')
    net = slim.fully_connected(net, 1000, activation_fn=None, scope='fc8')
  return net

2. tensorpack

tensorpack 是一个比较全面的工具包:

经典 CNNs 的 TensorFlow 实现资源汇总_第1张图片
tensorpack

GitHub 地址 : ppwwyyxx/tensorpack


3. TF-Tutorials

TF-Tutorials 是一个简短的教程,包括如下内容:

经典 CNNs 的 TensorFlow 实现资源汇总_第2张图片
tf-tutorials

GitHub 地址: awjuliani/TF-Tutorials


4. tflearn

经典 CNNs 的 TensorFlow 实现资源汇总_第3张图片
tflearn

GitHub 地址:tflearn/tflearn


5. Others

还有一些单一网络实现的工程,例如:

  • VGG: machrisaa/tensorflow-vgg
  • Faster RCNN: smallcorgi/Faster-RCNN_TF
  • SSD: seann999/ssd_tensorflow
  • YOLO: gliese581gg/YOLO_tensorflow
  • FCN: MarvinTeichmann/tensorflow-fcn
  • SegNet: tkuanlun350/Tensorflow-SegNet
  • DeepLab: DrSleep/tensorflow-deeplab-lfov, DrSleep/tensorflow-deeplab-resnet
  • Neural Style: anishathalye/neural-style
  • Pix2Pix: affinelayer/pix2pix-tensorflow
  • Colorization: shekkizh/Colorization.tensorflow
  • Depth Prediction: iro-cp/FCRN-DepthPrediction
  • Chessbot: Elucidation/tensorflow_chessbot
  • DCGAN: carpedm20/DCGAN-tensorflow
  • VAE-GAN: ikostrikov/TensorFlow-VAE-GAN-DRAW, timsainb/Tensorflow-MultiGPU-VAE-GAN
  • Mask RCNN: CharlesShang/FastMaskRCNN
  • ......

持续更新。。。。。。

你可能感兴趣的:(经典 CNNs 的 TensorFlow 实现资源汇总)