jiseshen
Busy trying to let the machine ask: "Who am I? Why did I say that? Whose kidneys are these?"
Fudan UniversityShanghai
Pinned Repositories
aspect-based-sentimental-classification-experiment
Reproduction of *A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis* and *Relational Graph Attention Network for Aspect-based Sentiment Analysis*, with the baseline as vanilla BERT classifier.
BasicSR
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
causal-inference-experiment
Carried on NSW dataset, using methods like regression, matching, weighting and DID.
CNN-experiments-on-CIFAR10
Some experiments to maximize the accuracy of image classification or the efficiency of training on CIFAR. Including ResNet, One Cycle Learning Rate, Cutout, etc.
deep-learning-experiments
express-logistics-system
Based on Django and MySQL, a deployable website featuring delivery management, temporary storage and user interface.
functa-experiment
Reproduction of *From data to functa: Your data point is a function and you can treat it like one* and *Spatial Functa: Scaling Functa to ImageNet Classification and Generation*.
novel-object-captioning-experiment
Reproduction of Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data and Captioning Images with Diverse Objects, with some minor changes in the equivocal points.
Prune
time-series-experiment
The data used is the geomagnetic data with hourly temporal solution. It is collected from Archived data of WDC for geomag., Kyoto., and the observation was done by Guam Observatory.
jiseshen's Repositories
jiseshen/express-logistics-system
Based on Django and MySQL, a deployable website featuring delivery management, temporary storage and user interface.
jiseshen/novel-object-captioning-experiment
Reproduction of Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data and Captioning Images with Diverse Objects, with some minor changes in the equivocal points.
jiseshen/aspect-based-sentimental-classification-experiment
Reproduction of *A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis* and *Relational Graph Attention Network for Aspect-based Sentiment Analysis*, with the baseline as vanilla BERT classifier.
jiseshen/BasicSR
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
jiseshen/causal-inference-experiment
Carried on NSW dataset, using methods like regression, matching, weighting and DID.
jiseshen/CNN-experiments-on-CIFAR10
Some experiments to maximize the accuracy of image classification or the efficiency of training on CIFAR. Including ResNet, One Cycle Learning Rate, Cutout, etc.
jiseshen/deep-learning-experiments
jiseshen/functa-experiment
Reproduction of *From data to functa: Your data point is a function and you can treat it like one* and *Spatial Functa: Scaling Functa to ImageNet Classification and Generation*.
jiseshen/Prune
jiseshen/time-series-experiment
The data used is the geomagnetic data with hourly temporal solution. It is collected from Archived data of WDC for geomag., Kyoto., and the observation was done by Guam Observatory.
jiseshen/user-profile-experiment
Using Weibo dataset and based on the data of history blogs, this project implements feature extraction to predict the user's gender, age and area. The features concerned include graph embedding, text embedding and Emoji embedding.