taki0112 / Densenet Tensorflow
Licence: mit
Simple Tensorflow implementation of Densenet using Cifar10, MNIST
Stars: ✭ 490
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Densenet Tensorflow
DenseNet-human-pose-estimation
Using DenseNet for human pose estimation based on TensorFlow.
Stars: ✭ 34 (-93.06%)
Mutual labels: densenet
DenseNet-MURA-PyTorch
Implementation of DenseNet model on Standford's MURA dataset using PyTorch
Stars: ✭ 59 (-87.96%)
Mutual labels: densenet
Densenet Caffe
DenseNet Caffe Models, converted from https://github.com/liuzhuang13/DenseNet
Stars: ✭ 350 (-28.57%)
Mutual labels: densenet
DenseNet-Cifar10
Train DenseNet on Cifar-10 based on Keras
Stars: ✭ 39 (-92.04%)
Mutual labels: densenet
pyro-vision
Computer vision library for wildfire detection
Stars: ✭ 33 (-93.27%)
Mutual labels: densenet
Awesome Computer Vision Models
A list of popular deep learning models related to classification, segmentation and detection problems
Stars: ✭ 278 (-43.27%)
Mutual labels: densenet
densenet
A PyTorch Implementation of "Densely Connected Convolutional Networks"
Stars: ✭ 50 (-89.8%)
Mutual labels: densenet
Ocr densenet
第一届西安交通大学人工智能实践大赛(2018AI实践大赛--图片文字识别)第一名;仅采用densenet识别图中文字
Stars: ✭ 425 (-13.27%)
Mutual labels: densenet
3ddensenet.torch
3D DenseNet(torch version) for ModelNet40 dataset
Stars: ✭ 43 (-91.22%)
Mutual labels: densenet
Tianchi Medical Lungtumordetect
天池医疗AI大赛[第一季]:肺部结节智能诊断 UNet/VGG/Inception/ResNet/DenseNet
Stars: ✭ 314 (-35.92%)
Mutual labels: densenet
Segmentation models
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Stars: ✭ 3,575 (+629.59%)
Mutual labels: densenet
CNN-Series-Getting-Started-and-PyTorch-Implementation
我的笔记和Demo,包含分类,检测、分割、知识蒸馏。
Stars: ✭ 49 (-90%)
Mutual labels: densenet
Basic cnns tensorflow2
A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).
Stars: ✭ 374 (-23.67%)
Mutual labels: densenet
pytorch-SRDenseNet
Pytorch implementation for SRDenseNet (ICCV2017)
Stars: ✭ 70 (-85.71%)
Mutual labels: densenet
Vision networks
Repo about neural networks for images handling
Stars: ✭ 266 (-45.71%)
Mutual labels: densenet
Awesome Very Deep Learning
♾A curated list of papers and code about very deep neural networks
Stars: ✭ 435 (-11.22%)
Mutual labels: densenet
Pytorch classification
利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码
Stars: ✭ 395 (-19.39%)
Mutual labels: densenet
Pytorch Hardnet
35% faster than ResNet: Harmonic DenseNet, A low memory traffic network
Stars: ✭ 293 (-40.2%)
Mutual labels: densenet
Densenet-Tensorflow
Tensorflow implementation of Densenet using Cifar10, MNIST
- The code that implements this paper is Densenet.py
- There is a slight difference, I used AdamOptimizer
If you want to see the original author's code or other implementations, please refer to this link
Requirements
- Tensorflow 1.x
- Python 3.x
- tflearn (If you are easy to use global average pooling, you should install tflearn
However, I implemented it using tf.layers, so don't worry
Issue
- I used tf.contrib.layers.batch_norm
def Batch_Normalization(x, training, scope):
with arg_scope([batch_norm],
scope=scope,
updates_collections=None,
decay=0.9,
center=True,
scale=True,
zero_debias_moving_mean=True) :
return tf.cond(training,
lambda : batch_norm(inputs=x, is_training=training, reuse=None),
lambda : batch_norm(inputs=x, is_training=training, reuse=True))
- If not enough GPU memory, Please edit the code
with tf.Session() as sess : NO
with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess : OK
Idea
What is the "Global Average Pooling" ?
def Global_Average_Pooling(x, stride=1) :
width = np.shape(x)[1]
height = np.shape(x)[2]
pool_size = [width, height]
return tf.layers.average_pooling2d(inputs=x, pool_size=pool_size, strides=stride)
# The stride value does not matter
- If you use tflearn, please refer to this link
def Global_Average_Pooling(x):
return tflearn.layers.conv.global_avg_pool(x, name='Global_avg_pooling')
What is the "Dense Connectivity" ?
What is the "Densenet Architecture" ?
def Dense_net(self, input_x):
x = conv_layer(input_x, filter=2 * self.filters, kernel=[7,7], stride=2, layer_name='conv0')
x = Max_Pooling(x, pool_size=[3,3], stride=2)
x = self.dense_block(input_x=x, nb_layers=6, layer_name='dense_1')
x = self.transition_layer(x, scope='trans_1')
x = self.dense_block(input_x=x, nb_layers=12, layer_name='dense_2')
x = self.transition_layer(x, scope='trans_2')
x = self.dense_block(input_x=x, nb_layers=48, layer_name='dense_3')
x = self.transition_layer(x, scope='trans_3')
x = self.dense_block(input_x=x, nb_layers=32, layer_name='dense_final')
x = Batch_Normalization(x, training=self.training, scope='linear_batch')
x = Relu(x)
x = Global_Average_Pooling(x)
x = Linear(x)
return x
What is the "Dense Block" ?
def dense_block(self, input_x, nb_layers, layer_name):
with tf.name_scope(layer_name):
layers_concat = list()
layers_concat.append(input_x)
x = self.bottleneck_layer(input_x, scope=layer_name + '_bottleN_' + str(0))
layers_concat.append(x)
for i in range(nb_layers - 1):
x = Concatenation(layers_concat)
x = self.bottleneck_layer(x, scope=layer_name + '_bottleN_' + str(i + 1))
layers_concat.append(x)
x = Concatenation(layers_concat)
return x
What is the "Bottleneck Layer" ?
def bottleneck_layer(self, x, scope):
with tf.name_scope(scope):
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
x = conv_layer(x, filter=4 * self.filters, kernel=[1,1], layer_name=scope+'_conv1')
x = Drop_out(x, rate=dropout_rate, training=self.training)
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch2')
x = Relu(x)
x = conv_layer(x, filter=self.filters, kernel=[3,3], layer_name=scope+'_conv2')
x = Drop_out(x, rate=dropout_rate, training=self.training)
return x
What is the "Transition Layer" ?
def transition_layer(self, x, scope):
with tf.name_scope(scope):
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
x = conv_layer(x, filter=self.filters, kernel=[1,1], layer_name=scope+'_conv1')
x = Drop_out(x, rate=dropout_rate, training=self.training)
x = Average_pooling(x, pool_size=[2,2], stride=2)
return x
Compare Structure (CNN, ResNet, DenseNet)
Results
- (MNIST) The highest test accuracy is 99.2% (This result does not use dropout)
- The number of dense block layers is fixed to 4
for i in range(self.nb_blocks) :
# original : 6 -> 12 -> 48
x = self.dense_block(input_x=x, nb_layers=4, layer_name='dense_'+str(i))
x = self.transition_layer(x, scope='trans_'+str(i))
CIFAR-10
CIFAR-100
Image Net
Related works
References
Author
Junho Kim
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].