Tips Tricks 20 - Understanding transfer learning for different size and channel inputs
Code generated in the video can be downloaded from here:
https://github.com/bnsreenu/python_for_microscopists
The input to the Vgg 16 model is 224x224x3 pixels images.
The Kernel size is 3x3 and the pool size is 2x2 for all the layers.
If our image size is different, can we still use transfer learning?
The answer is YES.
Input image size does not matter as the weights are associated with the filter kernel size. This does not change based on the input image size, for convolutional layers.
The number of channels does matter, as it affects the number of weights for the first convolutional layer. We can still use transfer learning by copying weights for the first channels from the original model and then filling the additional channel weights with the mean of existing weights along the channels.
Видео Tips Tricks 20 - Understanding transfer learning for different size and channel inputs канала DigitalSreeni
https://github.com/bnsreenu/python_for_microscopists
The input to the Vgg 16 model is 224x224x3 pixels images.
The Kernel size is 3x3 and the pool size is 2x2 for all the layers.
If our image size is different, can we still use transfer learning?
The answer is YES.
Input image size does not matter as the weights are associated with the filter kernel size. This does not change based on the input image size, for convolutional layers.
The number of channels does matter, as it affects the number of weights for the first convolutional layer. We can still use transfer learning by copying weights for the first channels from the original model and then filling the additional channel weights with the mean of existing weights along the channels.
Видео Tips Tricks 20 - Understanding transfer learning for different size and channel inputs канала DigitalSreeni
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![](https://i.ytimg.com/vi/sT1IF7PGoE4/default.jpg)
![158b - Transfer learning using CNN (VGG16) as feature extractor and Random Forest classifier](https://i.ytimg.com/vi/IuoEiemAuIY/default.jpg)
![91 - Introduction to transfer learning](https://i.ytimg.com/vi/LOvrfvtiC8c/default.jpg)
![Transfer Learning (C3W2L07)](https://i.ytimg.com/vi/yofjFQddwHE/default.jpg)
![What do filters of Convolution Neural Network learn?](https://i.ytimg.com/vi/eL80Im8Hq0k/default.jpg)
![154 - Understanding the training and validation loss curves](https://i.ytimg.com/vi/p3CcfIjycBA/default.jpg)
![Transfer Learning | Deep Learning Tutorial 27 (Tensorflow, Keras & Python)](https://i.ytimg.com/vi/LsdxvjLWkIY/default.jpg)
![260 - Identifying anomaly images using convolutional autoencoders](https://i.ytimg.com/vi/q_tpFGHiRgg/default.jpg)
![Transfer Learning and Fine-Tuning of a Pretrained Neural Network with Keras and TensorFlow](https://i.ytimg.com/vi/oHl8U3NccAE/default.jpg)
![210 - Multiclass U-Net using VGG, ResNet, and Inception as backbones](https://i.ytimg.com/vi/F365vQ8EndQ/default.jpg)
![Top 20 Microsoft Teams Tips & Tricks](https://i.ytimg.com/vi/w_NOLTAzDaQ/default.jpg)
![230 - Semantic Segmentation of Landcover Dataset using U-Net](https://i.ytimg.com/vi/0W6MKZqSke8/default.jpg)
![[DL] How to calculate the number of parameters in a convolutional neural network? Some examples](https://i.ytimg.com/vi/bikmA-VmSbY/default.jpg)
![235 - Pre-training U-net using autoencoders - Part 1 - Autoencoders and visualizing features](https://i.ytimg.com/vi/20af-_AQCBM/default.jpg)
![TensorFlow Tutorial 09 - Transfer Learning](https://i.ytimg.com/vi/8cN0PiZQl18/default.jpg)
![142 - Multilabel classification using Keras](https://i.ytimg.com/vi/hraKTseOuJA/default.jpg)
![73 - Image Segmentation using U-Net - Part1 (What is U-net?)](https://i.ytimg.com/vi/azM57JuQpQI/default.jpg)
![59 - What is Random Forest classifier?](https://i.ytimg.com/vi/6QSrgmMH4hE/default.jpg)
![Transfer Learning Using CNN(VGG 16)| Keras Tutorial|](https://i.ytimg.com/vi/lHM458ZsfkM/default.jpg)
![Loading in your own data - Deep Learning basics with Python, TensorFlow and Keras p.2](https://i.ytimg.com/vi/j-3vuBynnOE/default.jpg)