Skip to content
Snippets Groups Projects

Changes

Page history
  • New page
  • Templates
    • Update Basics of CNN authored by Cihan Ates's avatar Cihan Ates
    Hide whitespace changes
    Inline Side-by-side
    Showing
    with 19 additions and 25 deletions
    DDE-2/Basics-of-CNN.md
    View page @ 1e5fac49
    ...@@ -9,38 +9,27 @@ _C. Ates_ ...@@ -9,38 +9,27 @@ _C. Ates_
    ## Basics of CNNs ## Basics of CNNs
    - [An introduction to Convolutional Neural Networks](https://towardsdatascience.com/an-introduction-to-convolutional-neural-networks-eb0b60b58fd7) - [An introduction to Convolutional Neural Networks](https://towardsdatascience.com/an-introduction-to-convolutional-neural-networks-eb0b60b58fd7)
    - [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://arxiv.org/ftp/arxiv/papers/1901/1901.06032.pdf) - [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://arxiv.org/ftp/arxiv/papers/1901/1901.06032.pdf)
    ## How the kernel operation works? ## How the kernel operation works?
    .. ..
    ## Convolutional Autoencoders ## Convolutional Autoencoders
    - [Convolutional Autoencoders (CAE) with Tensorflow](https://ai.plainenglish.io/convolutional-autoencoders-cae-with-tensorflow-97e8d8859cbe) - [Convolutional Autoencoders (CAE) with Tensorflow](https://ai.plainenglish.io/convolutional-autoencoders-cae-with-tensorflow-97e8d8859cbe)
    - [Image Noise Reduction I](https://towardsdatascience.com/convolutional-autoencoders-for-image-noise-reduction-32fce9fc1763) - [Image Noise Reduction I](https://towardsdatascience.com/convolutional-autoencoders-for-image-noise-reduction-32fce9fc1763)
    - [Keras - image denoising](https://keras.io/examples/vision/autoencoder/) - [Keras - image denoising](https://keras.io/examples/vision/autoencoder/)
    - [Pre-Training CNNs Using Convolutional Autoencoders](https://www.ni.tu-berlin.de/fileadmin/fg215/teaching/nnproject/cnn_pre_trainin_paper.pdf) - [Pre-Training CNNs Using Convolutional Autoencoders](https://www.ni.tu-berlin.de/fileadmin/fg215/teaching/nnproject/cnn_pre_trainin_paper.pdf)
    ## Famous CNN Architectures ## Famous CNN Architectures
    - [CNN Literature](https://paperswithcode.com/methods/category/convolutional-neural-networks) - [CNN Literature](https://paperswithcode.com/methods/category/convolutional-neural-networks)
    - [Illustrated: 10 CNN Architectures I](https://towardsdatascience.com/illustrated-10-cnn-architectures-95d78ace614d) - [Illustrated: 10 CNN Architectures I](https://towardsdatascience.com/illustrated-10-cnn-architectures-95d78ace614d)
    - [Illustrated: 10 CNN Architectures II](https://towardsdatascience.com/top-10-cnn-architectures-every-machine-learning-engineer-should-know-68e2b0e07201) - [Illustrated: 10 CNN Architectures II](https://towardsdatascience.com/top-10-cnn-architectures-every-machine-learning-engineer-should-know-68e2b0e07201)
    - [AlexNet to EfficientNet](https://theaisummer.com/cnn-architectures/) - [AlexNet to EfficientNet](https://theaisummer.com/cnn-architectures/)
    - [DenseNet Literature](https://paperswithcode.com/method/densenet) - [DenseNet Literature](https://paperswithcode.com/method/densenet)
    - [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946) - [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946)
    - [HRNet](https://paperswithcode.com/method/hrnet) - [HRNet](https://paperswithcode.com/method/hrnet)
    ## Using pre-trained models in TF ## Using pre-trained models in TF
    ...@@ -50,32 +39,38 @@ _C. Ates_ ...@@ -50,32 +39,38 @@ _C. Ates_
    - [Transfer learning with TensorFlow](https://www.tensorflow.org/tutorials/images/transfer_learning_with_hub) - [Transfer learning with TensorFlow](https://www.tensorflow.org/tutorials/images/transfer_learning_with_hub)
    ### Additional notebooks on transfer learning -- Melanoma Case ### Additional notebooks on transfer learning -- Melanoma Case
    <br /><a href="https://keras.io/api/applications/">Available </a>models<br /><br /><a href="https://www.kaggle.com/franvaluch/easy-skin-cancer-detection-cnn-resnet-vgg16#VGG16">Notebook</a>: CNN+ResNet+VGG16<br /><br /><a href="https://www.kaggle.com/nxrprime/siim-d3-eda-augmentations-and-resnext#seven">Notebook</a>: ResNet<br /><br /><a href="https://www.kaggle.com/gokulzuzumaki/melonama-skin-cancerclassification-efficientnet">Notebook</a>: <span class="nc">EfficientNet<br /><br /><a href="https://www.kaggle.com/ibtesama/melanoma-classification-with-attention#Model-:-VGG16-with-Attention">Notebook</a>: VGG16 with Attention<br /><br /><a href="vgg19%20">Notebook</a>: VGG19<br /><br /><a href="https://www.kaggle.com/sukanthen/cnn-architectures-custom-and-transfer-learning#7)-NASNet">Notebook</a>: NASNet</span><br /><br /><a href="https://github.com/Masdevallia/3rd-place-kaggle-siim-isic-melanoma-classification">Code</a>: ensemble of 8 different models<br /><br />Extended <a href="https://www.kaggle.com/zainahmad/eda-melanoma-classification-using-tensorflow/notebook#model-creation-and-training">dataset </a>notebook<br />
    [Available ](https://keras.io/api/applications/)models\
    \
    [Notebook](https://www.kaggle.com/franvaluch/easy-skin-cancer-detection-cnn-resnet-vgg16#VGG16): CNN+ResNet+VGG16\
    \
    [Notebook](https://www.kaggle.com/nxrprime/siim-d3-eda-augmentations-and-resnext#seven): ResNet\
    \
    [Notebook](https://www.kaggle.com/gokulzuzumaki/melonama-skin-cancerclassification-efficientnet): <span dir="">EfficientNet\
    \
    </span>[<span dir="">Notebook</span>](https://www.kaggle.com/ibtesama/melanoma-classification-with-attention#Model-:-VGG16-with-Attention)<span dir="">: VGG16 with Attention\
    \
    </span>[<span dir="">Notebook</span>](vgg19%20)<span dir="">: VGG19\
    \
    </span>[<span dir="">Notebook</span>](https://www.kaggle.com/sukanthen/cnn-architectures-custom-and-transfer-learning#7)-NASNet)<span dir="">: NASNet</span>\
    \
    [Code](https://github.com/Masdevallia/3rd-place-kaggle-siim-isic-melanoma-classification): ensemble of 8 different models\
    \
    Extended [dataset ](https://www.kaggle.com/zainahmad/eda-melanoma-classification-using-tensorflow/notebook#model-creation-and-training)notebook
    ## YOLO: You Only Look Once ## YOLO: You Only Look Once
    - [What is YOLO?](https://jonathan-hui.medium.com/yolov4-c9901eaa8e61) - [What is YOLO?](https://jonathan-hui.medium.com/yolov4-c9901eaa8e61)
    - [What is YOLO -- alternative](https://blog.roboflow.com/a-thorough-breakdown-of-yolov4/) - [What is YOLO -- alternative](https://blog.roboflow.com/a-thorough-breakdown-of-yolov4/)
    - [YOLO Paper](https://arxiv.org/abs/2004.10934) - [YOLO Paper](https://arxiv.org/abs/2004.10934)
    - [Darknet Repo](https://github.com/AlexeyAB/darknet#how-to-use-on-the-command-line) - [Darknet Repo](https://github.com/AlexeyAB/darknet#how-to-use-on-the-command-line)
    - [How to Perform Object Detection With YOLOv3 in Keras](https://machinelearningmastery.com/how-to-perform-object-detection-with-yolov3-in-keras/) - [How to Perform Object Detection With YOLOv3 in Keras](https://machinelearningmastery.com/how-to-perform-object-detection-with-yolov3-in-keras/)
    - [YOLO repo](https://github.com/hunglc007/tensorflow-yolov4-tflite) - [YOLO repo](https://github.com/hunglc007/tensorflow-yolov4-tflite)
    - [YOLO v5](https://towardsdatascience.com/how-to-train-a-custom-object-detection-model-with-yolo-v5-917e9ce13208) - [YOLO v5](https://towardsdatascience.com/how-to-train-a-custom-object-detection-model-with-yolo-v5-917e9ce13208)
    - [YOLO pypi.org](https://pypi.org/project/yolov4/) - [YOLO pypi.org](https://pypi.org/project/yolov4/)
    - [YOLOv4 implementation with Tensorflow 2](https://pypi.org/project/tf-yolov4/) - [YOLOv4 implementation with Tensorflow 2](https://pypi.org/project/tf-yolov4/)
    - [Train a Custom Mobile Object Detection Model with YOLO](https://blog.roboflow.com/how-to-train-a-custom-mobile-object-detection-model/) - [Train a Custom Mobile Object Detection Model with YOLO](https://blog.roboflow.com/how-to-train-a-custom-mobile-object-detection-model/)
    - [Anchor Boxes: why important?](https://towardsdatascience.com/anchor-boxes-the-key-to-quality-object-detection-ddf9d612d4f9) - [Anchor Boxes: why important?](https://towardsdatascience.com/anchor-boxes-the-key-to-quality-object-detection-ddf9d612d4f9)
    - [Feature Pyramid Networks for Object Detection](https://arxiv.org/pdf/1612.03144.pdf) - [Feature Pyramid Networks for Object Detection](https://arxiv.org/pdf/1612.03144.pdf)
    ## Image Databases and Benchmarks ## Image Databases and Benchmarks
    ...@@ -84,7 +79,6 @@ _C. Ates_ ...@@ -84,7 +79,6 @@ _C. Ates_
    ## Selected CNN Applications ## Selected CNN Applications
    \
    \ \
    [Build a CNN network to predict 3D bounding box of car from 2D image:](https://awesomeopensource.com/project/experiencor/image-to-3d-bbox)\ [Build a CNN network to predict 3D bounding box of car from 2D image:](https://awesomeopensource.com/project/experiencor/image-to-3d-bbox)\
    \ \
    ......

    Help | Imprint | Privacy policy | Accessibility | Contact