Image recognition
Image generation
Image segmentation
sample_CLIP
We build a training-free image classification model using the CLIP plug-in of the NNC. We use flower and food images as sample data.
wav_keyboard_sound
Distinguish between four keyboard tap sounds (membrane, pantograph, mechanical blue switch and mechanical red switch)
tutorial.NLP.20newsgroups_classification
Text binary classification
tutorial.NLP.20newsgroups_lstm_language_model.sdcproj
Language model using LSTM
tutorial.NLP.20newsgroups_transformer_language_model.sdcproj
Language model using Transformer
tutorial.NLP.20newsgroups_word_embedding.sdcproj
Word embedding using CBOW (Word2vec)
tutorial.anomaly_detection.sin_wave_anomaly_detection
Anormary detection from sin wave using auto encoder
tutorial.object_detection.synthetic_image_object_detection
Object detection using synthetic image data including ellipse, triangle, rectangle and pentagon
tutorial.object_detection.synthetic_image_object_detection_centernet
Object detection using CenterNet. Backbone is ResNet-18.
classification.iris.iris
Vector classification on iris flower dataset
classification.adult.adult
Vector classification on adult dataset
Search by purpose
>
Image recognition
tutorial.basics.01_logistic_regression
Image binary classification using the simplest one-layer neural networks
tutorial.basics.02_binary_cnn
Image binary classification using 4-layer convolutional neural networks
tutorial.basics.10_deep_mlp
Deep neural networks
tutorial.basics.12_residual_learning
Image classification using residual networks on MNIST dataset
tutorial.binary_networks.binary_connect_mnist_MLP
DNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_connect_mnist_LeNet
CNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_net_mnist_MLP
DNN that consumes much less memory and computation by weight and data path binalization
tutorial.binary_networks.binary_net_mnist_LeNet
CNN that consumes much less memory and computation by weight and data path binalization
tutorial.binary_networks.binary_weight_mnist_MLP
DNN that consumes much less memory by weight binalization
tutorial.recurrent_neural_networks.elman_net
The simplest recurrent neural networks
tutorial.recurrent_neural_networks.bidirectional_elman_net
Bi-directional recurrent neural networks
tutorial.recurrent_neural_networks.elman_net_with_attention
Recurrent neural networks with attention
tutorial.recurrent_neural_networks.gated_recurrent_unit(GRU)
Gated recurrent unit (GRU)
tutorial.recurrent_neural_networks.long_short_term_memory(LSTM)
Long short term memory (LSTM)
tutorial.recurrent_neural_networks.stacked_GRU
Recurrent neural networks with 2 GRUs
tutorial.image_classification.hand-sign
Example of 4-class hand-sign image classification for SPRESENSE
tutorial.image_classification.digits
Example of 11-class digits image classification for SPRESENSE
tutorial.explainable_dl.01_visualize_weight_of_feature
Visualization method of importance of input data by learning weight of input data
tutorial.explainable_dl.02_l1_regularization
Visualization method of importance of input data using L1 regularization
tutorial.explainable_dl.03_attention
Visualization method of attention area
tutorial.explainable_dl.04_inference_result_at_each_layer
Visualization method to check output of each data path
tutorial.explainable_dl.05_MCdropout
Visualization method of reliability of prediction results by neural networks
image_recognition.MNIST.LeNet
Image classification using 4-layer convolutional neural networks on MNIST dataset
image_recognition.MNIST.semi_supervised_learning_VAT
Semi-supervised learning using variational auto encoder
image_recognition.FashionMNIST.LeNet
Image classification using 4-layer convolutional neural networks on Fashion-MNIST dataset
image_recognition.CIFAR10.resnet.resnet-110-deepmil
Weakly supervised image localizaion
image_recognition.CIFAR10.resnet.resnet-110-cutout
Image augmentation by masking part of an image
image_recognition.CIFAR10.resnet.resnet-110-mixup
Image augmentation by blending 2 images
image_recognition.CIFAR10.resnet.resnet-110
Image classification using residual networks on CIFAR-10 dataset
image_recognition.CIFAR100.resnet.resnet-110
Image classification using residual networks on CIFAR-100 dataset
image_recognition.ILSVRC2012.densenet.densenet-161
Light weight neural networks that express shallow and deep networks simultaneously
image_recognition.ILSVRC2012.residual networks.resnet-101
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-152
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-18
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-34
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-50
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.resnext.resnext-101
Residual networks with grouped convolution
image_recognition.ILSVRC2012.shufflenet.shufflenet-0.5x
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.shufflenet.shufflenet-2.0x
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.shufflenet.shufflenet
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.squeezenet.squeezenet11
Light weight convolutional neural networks with bottle-neck structure
image_recognition.ILSVRC2012.vgg.vgg-11
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.vgg.vgg-13
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.vgg.vgg-16
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.alexnet
Neural networks for image classification which is the winner of the ImageNet challenge 2012
image_recognition.ILSVRC2012.GoogLeNet
Neural networks for image classification which is the winner of the ImageNet challenge 2014
image_recognition.ILSVRC2012.nin
Network in networks
image_recognition.ILSVRC2012.senet-154
ResNeXt with "Squeese and Excitation" block
Search by purpose
>
Image generation
tutorial.super_resolution
A sample project for image super-resolution that takes a low-resolution image input and outputs a high-resolution image.
tutorial.basics.06_auto_encoder
Auto encoder
tutorial.basics.11_deconvolution
Convolutional auto encoder
tutorial.recurrent_neural_networks.LSTM_auto_encoder
Auto encoder using LSTM
image_generation.mnist_dcgan
Deep Convolutional Generative Adversarial Networks(DCGAN)
image_generation.mnist_dcgan_with_label
Deep Convolutional Generative Adversarial Networks(DCGAN)
image_generation.mnist_vae
Variational auto encoder (VAE)
Search by purpose
>
Image segmentation
tutorial.semantic_segmentation.binary_semantic_segmentation
Binary segmentation to separate letters and background
tutorial.semantic_segmentation.unetlike_125px
20 class semantic segmentation using U-Net
tutorial.semantic_segmentation.unetlike_125px_person
2 class semantic segmentation using U-Net
tutorial.semantic_segmentation.binary_semantic_segmentation_FCN-VGG16
2 class semantic segmentation using FCN. Backbone is VGG16.
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50_Remodeling
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_DeepLabV3plus
2 class semantic segmentation using DeepLabV3. Backbone is Xception.
CNN
ResNet
DNN
BNN
RNN
sample_CLIP
We build a training-free image classification model using the CLIP plug-in of the NNC. We use flower and food images as sample data.
tutorial.NLP.20newsgroups_lstm_language_model.sdcproj
Language model using LSTM
tutorial.NLP.20newsgroups_transformer_language_model.sdcproj
Language model using Transformer
tutorial.NLP.20newsgroups_word_embedding.sdcproj
Word embedding using CBOW (Word2vec)
tutorial.basics.01_logistic_regression
Image binary classification using the simplest one-layer neural networks
tutorial.basics.06_auto_encoder
Auto encoder
tutorial.basics.11_deconvolution
Convolutional auto encoder
tutorial.anomaly_detection.sin_wave_anomaly_detection
Anormary detection from sin wave using auto encoder
Search by technique
>
CNN
tutorial.basics.02_binary_cnn
Image binary classification using 4-layer convolutional neural networks
tutorial.image_classification.hand-sign
Example of 4-class hand-sign image classification for SPRESENSE
tutorial.image_classification.digits
Example of 11-class digits image classification for SPRESENSE
tutorial.explainable_dl.04_inference_result_at_each_layer
Visualization method to check output of each data path
tutorial.explainable_dl.05_MCdropout
Visualization method of reliability of prediction results by neural networks
image_recognition.FashionMNIST.LeNet
Image classification using 4-layer convolutional neural networks on Fashion-MNIST dataset
tutorial.semantic_segmentation.binary_semantic_segmentation
Binary segmentation to separate letters and background
image_recognition.MNIST.LeNet
Image classification using 4-layer convolutional neural networks on MNIST dataset
image_recognition.CIFAR10.resnet.resnet-110
Image classification using residual networks on CIFAR-10 dataset
image_recognition.CIFAR100.resnet.resnet-110
Image classification using residual networks on CIFAR-100 dataset
image_recognition.ILSVRC2012.densenet.densenet-161
Light weight neural networks that express shallow and deep networks simultaneously
image_recognition.ILSVRC2012.shufflenet.shufflenet-0.5x
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.shufflenet.shufflenet-2.0x
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.shufflenet.shufflenet
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.squeezenet.squeezenet11
Light weight convolutional neural networks with bottle-neck structure
image_recognition.ILSVRC2012.vgg.vgg-11
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.vgg.vgg-13
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.vgg.vgg-16
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.alexnet
Neural networks for image classification which is the winner of the ImageNet challenge 2012
image_recognition.ILSVRC2012.GoogLeNet
Neural networks for image classification which is the winner of the ImageNet challenge 2014
image_recognition.ILSVRC2012.nin
Network in networks
tutorial.basics.12_residual_learning
Image classification using residual networks on MNIST dataset
image_recognition.ILSVRC2012.residual networks.resnet-18
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-34
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-50
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-101
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-152
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.resnext.resnext-101
Residual networks with grouped convolution
image_recognition.ILSVRC2012.senet-154
ResNeXt with "Squeese and Excitation" block
tutorial.binary_networks.binary_connect_mnist_LeNet
CNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_net_mnist_LeNet
CNN that consumes much less memory and computation by weight and data path binalization
tutorial.semantic_segmentation.unetlike_125px
20 class semantic segmentation using U-Net
tutorial.semantic_segmentation.unetlike_125px_person
2 class semantic segmentation using U-Net
wav_keyboard_sound
Distinguish between four keyboard tap sounds (membrane, pantograph, mechanical blue switch and mechanical red switch)
tutorial.semantic_segmentation.binary_semantic_segmentation_FCN-VGG16
2 class semantic segmentation using FCN. Backbone is VGG16.
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50_Remodeling
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_DeepLabV3plus
2 class semantic segmentation using DeepLabV3. Backbone is Xception.
image_generation.mnist_dcgan_with_label
Deep Convolutional Generative Adversarial Networks(DCGAN)
image_generation.mnist_dcgan
Deep Convolutional Generative Adversarial Networks(DCGAN)
image_recognition.CIFAR10.resnet.resnet-110-deepmil
Weakly supervised image localizaion
image_recognition.CIFAR10.resnet.resnet-110-cutout
Image augmentation by masking part of an image
image_recognition.CIFAR10.resnet.resnet-110-mixup
Image augmentation by blending 2 images
tutorial.object_detection.synthetic_image_object_detection
Object detection using synthetic image data including ellipse, triangle, rectangle and pentagon
tutorial.object_detection.synthetic_image_object_detection_centernet
Object detection using CenterNet. Backbone is ResNet-18.
Search by technique
>
ResNet
tutorial.basics.12_residual_learning
Image classification using residual networks on MNIST dataset
image_recognition.ILSVRC2012.residual networks.resnet-18
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-34
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-50
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-101
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-152
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.resnext.resnext-101
Residual networks with grouped convolution
image_recognition.ILSVRC2012.senet-154
ResNeXt with "Squeese and Excitation" block
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50_Remodeling
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_DeepLabV3plus
2 class semantic segmentation using DeepLabV3. Backbone is Xception.
Search by technique
>
DNN
tutorial.basics.10_deep_mlp
Deep neural networks
tutorial.binary_networks.binary_connect_mnist_MLP
DNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_net_mnist_MLP
DNN that consumes much less memory and computation by weight and data path binalization
tutorial.binary_networks.binary_weight_mnist_MLP
DNN that consumes much less memory by weight binalization
tutorial.explainable_dl.01_visualize_weight_of_feature
Visualization method of importance of input data by learning weight of input data
tutorial.explainable_dl.02_l1_regularization
Visualization method of importance of input data using L1 regularization
tutorial.explainable_dl.03_attention
Visualization method of attention area
classification.iris.iris
Vector classification on iris flower dataset
tutorial.super_resolution
A sample project for image super-resolution that takes a low-resolution image input and outputs a high-resolution image.
image_generation.mnist_vae
Variational auto encoder (VAE)
image_recognition.MNIST.semi_supervised_learning_VAT
Semi-supervised learning using variational auto encoder
classification.adult.adult
Vector classification on adult dataset
tutorial.NLP.20newsgroups_classification
Text binary classification
Search by technique
>
BNN
tutorial.binary_networks.binary_connect_mnist_MLP
DNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_connect_mnist_LeNet
CNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_net_mnist_MLP
DNN that consumes much less memory and computation by weight and data path binalization
tutorial.binary_networks.binary_net_mnist_LeNet
CNN that consumes much less memory and computation by weight and data path binalization
tutorial.binary_networks.binary_weight_mnist_MLP
DNN that consumes much less memory by weight binalization
Search by technique
>
RNN
tutorial.recurrent_neural_networks.elman_net
The simplest recurrent neural networks
tutorial.recurrent_neural_networks.bidirectional_elman_net
Bi-directional recurrent neural networks
tutorial.recurrent_neural_networks.elman_net_with_attention
Recurrent neural networks with attention
tutorial.recurrent_neural_networks.gated_recurrent_unit(GRU)
Gated recurrent unit (GRU)
tutorial.recurrent_neural_networks.long_short_term_memory(LSTM)
Long short term memory (LSTM)
tutorial.recurrent_neural_networks.LSTM_auto_encoder
Auto encoder using LSTM
tutorial.recurrent_neural_networks.stacked_GRU
Recurrent neural networks with 2 GRUs
small MNIST
MNIST
ImageNet
CIFAR-10/100
20NewsGroups
sample_CLIP
We build a training-free image classification model using the CLIP plug-in of the NNC. We use flower and food images as sample data.
tutorial.super_resolution
A sample project for image super-resolution that takes a low-resolution image input and outputs a high-resolution image.
tutorial.image_classification.hand-sign
Example of 4-class hand-sign image classification for SPRESENSE
tutorial.image_classification.digits
Example of 11-class digits image classification for SPRESENSE
synthetic_image.binary_segmentation
tutorial.semantic_segmentation.unetlike_125px
20 class semantic segmentation using U-Net
tutorial.semantic_segmentation.unetlike_125px_person
2 class semantic segmentation using U-Net
tutorial.anomaly_detection.sin_wave_anomaly_detection
Anormary detection from sin wave using auto encoder
tutorial.object_detection.synthetic_image_object_detection
Object detection using synthetic image data including ellipse, triangle, rectangle and pentagon
tutorial.object_detection.synthetic_image_object_detection_centernet
Object detection using CenterNet. Backbone is ResNet-18.
wav_keyboard_sound
Distinguish between four keyboard tap sounds (membrane, pantograph, mechanical blue switch and mechanical red switch)
classification.iris.iris
Vector classification on iris flower dataset
classification.adult.adult
Vector classification on adult dataset
Search by dataset
>
small MNIST
tutorial.basics.01_logistic_regression
Image binary classification using the simplest one-layer neural networks
tutorial.basics.02_binary_cnn
Image binary classification using 4-layer convolutional neural networks
tutorial.basics.06_auto_encoder
Auto encoder
tutorial.basics.10_deep_mlp
Deep neural networks
tutorial.basics.11_deconvolution
Convolutional auto encoder
tutorial.recurrent_neural_networks.elman_net
The simplest recurrent neural networks
tutorial.recurrent_neural_networks.bidirectional_elman_net
Bi-directional recurrent neural networks
tutorial.recurrent_neural_networks.elman_net_with_attention
Recurrent neural networks with attention
tutorial.recurrent_neural_networks.gated_recurrent_unit(GRU)
Gated recurrent unit (GRU)
tutorial.recurrent_neural_networks.long_short_term_memory(LSTM)
Long short term memory (LSTM)
tutorial.recurrent_neural_networks.LSTM_auto_encoder
Auto encoder using LSTM
tutorial.recurrent_neural_networks.stacked_GRU
Recurrent neural networks with 2 GRUs
tutorial.explainable_dl.01_visualize_weight_of_feature
Visualization method of importance of input data by learning weight of input data
tutorial.explainable_dl.02_l1_regularization
Visualization method of importance of input data using L1 regularization
tutorial.explainable_dl.03_attention
Visualization method of attention area
tutorial.explainable_dl.04_inference_result_at_each_layer
Visualization method to check output of each data path
tutorial.explainable_dl.05_MCdropout
Visualization method of reliability of prediction results by neural networks
Search by dataset
>
MNIST
tutorial.basics.12_residual_learning
Image classification using residual networks on MNIST dataset
tutorial.binary_networks.binary_connect_mnist_MLP
DNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_connect_mnist_LeNet
CNN that consumes much less memory by weight binalization
tutorial.binary_networks.binary_net_mnist_MLP
DNN that consumes much less memory and computation by weight and data path binalization
tutorial.binary_networks.binary_net_mnist_LeNet
CNN that consumes much less memory and computation by weight and data path binalization
tutorial.binary_networks.binary_weight_mnist_MLP
DNN that consumes much less memory by weight binalization
image_recognition.MNIST.LeNet
Image classification using 4-layer convolutional neural networks on MNIST dataset
image_recognition.MNIST.semi_supervised_learning_VAT
Semi-supervised learning using variational auto encoder
image_recognition.FashionMNIST.LeNet
Image classification using 4-layer convolutional neural networks on Fashion-MNIST dataset
image_generation.mnist_dcgan
Deep Convolutional Generative Adversarial Networks(DCGAN)
image_generation.mnist_dcgan_with_label
Deep Convolutional Generative Adversarial Networks(DCGAN)
image_generation.mnist_vae
Variational auto encoder (VAE)
Search by dataset
>
ImageNet
image_recognition.ILSVRC2012.densenet.densenet-161
Light weight neural networks that express shallow and deep networks simultaneously
image_recognition.ILSVRC2012.residual networks.resnet-101
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-152
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-18
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-34
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.residual networks.resnet-50
Neural networks for image classification which is the winner of the ImageNet challenge 2015
image_recognition.ILSVRC2012.resnext.resnext-101
Residual networks with grouped convolution
image_recognition.ILSVRC2012.shufflenet.shufflenet-0.5x
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.shufflenet.shufflenet-2.0x
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.shufflenet.shufflenet
Light weight convolutional neural networks with shuffle structure
image_recognition.ILSVRC2012.squeezenet.squeezenet11
Light weight convolutional neural networks with bottle-neck structure
image_recognition.ILSVRC2012.vgg.vgg-11
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.vgg.vgg-13
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.vgg.vgg-16
Neural networks for image classification which is the winner of the ImageNet challenge 2013
image_recognition.ILSVRC2012.alexnet
Neural networks for image classification which is the winner of the ImageNet challenge 2012
image_recognition.ILSVRC2012.GoogLeNet
Neural networks for image classification which is the winner of the ImageNet challenge 2014
image_recognition.ILSVRC2012.nin
Network in networks
image_recognition.ILSVRC2012.senet-154
ResNeXt with "Squeese and Excitation" block
Search by dataset
>
CIFAR-10/100
image_recognition.CIFAR10.resnet.resnet-110-deepmil
Weakly supervised image localizaion
image_recognition.CIFAR10.resnet.resnet-110-cutout
Image augmentation by masking part of an image
image_recognition.CIFAR10.resnet.resnet-110-mixup
Image augmentation by blending 2 images
image_recognition.CIFAR10.resnet.resnet-110
Image classification using residual networks on CIFAR-10 dataset
image_recognition.CIFAR100.resnet.resnet-110
Image classification using residual networks on CIFAR-100 dataset
Search by dataset
>
20NewsGroups
tutorial.NLP.20newsgroups_classification
Text binary classification
tutorial.NLP.20newsgroups_lstm_language_model.sdcproj
Language model using LSTM
tutorial.NLP.20newsgroups_transformer_language_model.sdcproj
Language model using Transformer
tutorial.NLP.20newsgroups_word_embedding.sdcproj
Word embedding using CBOW (Word2vec)
Search by dataset
>
synthetic_image.binary_segmentation
tutorial.semantic_segmentation.binary_semantic_segmentation
Binary segmentation to separate letters and background
tutorial.semantic_segmentation.binary_semantic_segmentation_FCN-VGG16
2 class semantic segmentation using FCN. Backbone is VGG16.
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_PSPNet-ResNet50_Remodeling
2 class semantic segmentation using PSPNet. Backbone is resnet-50. Deconvolution layer is used for upsampling instead of linear completion.
tutorial.semantic_segmentation.binary_semantic_segmentation_DeepLabV3plus
2 class semantic segmentation using DeepLabV3. Backbone is Xception.
