Scribd
Upload
52 views12 pages

Very Deep Convolutional Networks For Large-Scale Image Recognition

The document discusses VGG16, a convolutional neural network architecture. It describes using VGG16 for large-scale image recognition, the architecture, input sizes, libraries that can use the pre-trained model, advantages like being easy to implement and transfer learning, and limitations like being slow to train and large model size.

Uploaded by

Estefania Cadena Gaona
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
52 views12 pages

Very Deep Convolutional Networks For Large-Scale Image Recognition

The document discusses VGG16, a convolutional neural network architecture. It describes using VGG16 for large-scale image recognition, the architecture, input sizes, libraries that can use the pre-trained model, advantages like being easy to implement and transfer learning, and limitations like being slow to train and large model size.

Uploaded by

Estefania Cadena Gaona
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

Very Deep

Convolutional
Networks for
Large-Scale Image
Recognition
Sergio Alejandro Camacho Cano
Juan Diego Olaya Olivera
Daniel Alejandro Aguilar Meneses
Identificación de imágenes que se pueden hacer
Imágenes a gran escala, usando datasets como:

INRIA Aerial Image Labeling ImageNet GTAV


Arquitectura VGG16

Para hacer esta arquitectura se uso un database de perros vs gatos


Arquitectura VGG16
CNN Arquitectura
Resoluciones de imágenes de entrada puede recibir
The default input size for this model is 224x224.
Librerías donde se puede usar pre entrenado
Se puede usar Pythorch, nnabla y Keras.

Arguments

● include_top: whether to include the 3 fully-connected layers at the top of the network.
● weights: one of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded.
● input_tensor: optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
● input_shape: optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (224, 224, 3)
(with channels_last data format) or (3, 224, 224) (with channels_first data format). It should have exactly 3 input channels, and
width and height should be no smaller than 32. E.g. (200, 200, 3) would be one valid value.
● pooling: Optional pooling mode for feature extraction when include_top is False. - None means that the output of the model will
be the 4D tensor output of the last convolutional block. - avg means that global average pooling will be applied to the output of
the last convolutional block, and thus the output of the model will be a 2D tensor. - max means that global max pooling will be
applied.
● classes: optional number of classes to classify images into, only to be specified if include_top is True, and if no weights
argument is specified.
● classifier_activation: A str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set
classifier_activation=None to return the logits of the "top" layer. When loading pretrained weights, classifier_activation can only
be None or "softmax".
Ventajas
In spite of these, the following advantages outweigh the drawbacks.

1. It is easy to implement and is a great building block for learning purposes.

2. VGG16 can be pre-trained on ImageNet.

VGG16 can be used for transfer learning. The detailed implementation of VGG16 using Python

code is described in the training section, above.


Limitaciones
The two major drawbacks with VGG Net are:

1. It is very slow to train.

2. The weights of the network architecture are quite large themselves (a concern for disk

and bandwidth)
Notebook
https://colab.research.google.com/drive/1g_qc4h8sFlR__duAcw-W06aGP2ZTcjlv?usp=sharing
Bibliografía
● Team, K. (s. f.). Keras documentation: VGG16 and VGG19. Keras.Io. https://keras.io/api/applications/vgg/

● Great Learning. (2022, 5 enero). What is VGG16? — Introduction to VGG16 - Great Learning. Medium. https://medium.com/@mygreatlearning/what-

is-vgg16-introduction-to-vgg16-f2d63849f615

● Simonyan, K. (2014, 4 septiembre). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.Org. https://arxiv.org/abs/1409.1556

● nnabla.models.imagenet.vgg — Neural Network Libraries 1.26.0 documentation. (s. f.). Nnabla.Readthedocs.Io.

https://nnabla.readthedocs.io/en/latest/_modules/nnabla/models/imagenet/vgg.html

● PyTorch. (s. f.). Pytorch.Org. https://pytorch.org/hub/pytorch_vision_vgg/

● Team, K. (s. f.). Keras documentation: Keras Applications. Keras.Io. https://keras.io/api/applications/

● Goswani Saptarsi. (2020, octubre 20) https://towardsdatascience.com/how-to-use-a-pre-trained-model-vgg-for-image-classification-8dd7c4a4a517

You might also like