official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"

[CVPR 2021] Self-supervised depth estimation from short sequences

Mono depth estimation for self-driving cars 🚗

Stereo depth estimation for self-driving cars 🚗

Unsupervised single image depth prediction with CNNs

Reaction diffusion system prediction based on convolutional neural network

CNN神经网络细胞形态彩色图像识别数据集制作，训练，预测

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

项目名称为：自建数据集人脸识别。该项目利用电脑自带摄像头或者已有照片进行人脸数据集建立，再进行人脸检测，人脸识别，人脸预测，包括数据采集、数据预处理、建模、模型训练、模型使用预测全过程。项目使用Openc3进行数据采集、数据预处理，Keras 进行建模，模型参考了VGG16网络，包含4个卷积层，5个LeRu层，2个池化层，3个Dropout层，2个全连接层，1个flatten层，1个分类层，…

Using FCN to detect traffic lights in images

Implementation of FCN (8/16/32) in Tensorflow. 🌀 在TensorFlow框架下实现 FCN (全卷积神经网络) 。

Image segmentation with keras. FCN, Unet, DeepLab V3 plus, Mask RCNN ... etc.

Inspired by the success and computational efficiency of convolutional architectures for various sequential tasks compared to recurrent neural networks. We explored CNN and RCNN autoencoder whose re…

Feature Map Inversion to visualize what feature a filter extract from input image in CNNs

Simple depth maps obtained by using CNN

A complete tutorial on using own dataset to train a CNN from scratch in Keras (TF & Theano Backend)-

A simple binary classifier to predict if the given image is a cat or a dog.

A Tensorflow implementation of CNN-LSTM image caption generator architecture that achieves close to state-of-the-art results on the MSCOCO dataset.

记录自己在学习neural_network过程中做的一些工作

Training a convolutional neural network using own picture dataset

facial emotion recognition with CNN and LSTM

Predict Vehicle collision moments before it happens in Carla!. CNN and LSTM hybrid architecture is used to understand a series of images.