[SOLVED] deep learning network code (https://colab.research.google.com/drive/12RHsJkoIsc1fuMYkI3YLji96fABMPrON) Option (1):

code (https://colab.research.google.com/drive/12RHsJkoIsc1fuMYkI3YLji96fABMPrON) Option (1):
Convolutional neural networks Train a convolutional neural networks method on Tiny ImageNet dataset (http://pages.ucsd.edu/~ztu/courses/tiny-imagenet-200.zip) You can choose any deep learning platforms including PyTorch (https://pytorch.org), TensorFlow (https://www.tensorflow.org), train a model by building your own network structure or by adopting/following standard networks like AlexNet, GoogLeNet, VGG, etc. Code by yourself.
Check Point:
Tuning hyper-parameters in your final project will need to be more comprehensive that what was done in HW4.
( https://colab.research.google.com/drive/1sXRHBTDHWbYgLWnIa5VI9hCLvU8OqBt J)
For example, if you are performing CNN classification on the Tiny ImageNet dataset, some options to consider include
a. Comparing two different architectures chosen from e.g. LeNet, AlexNet, VGG, GoogleNet or ResNet ()
b. Trying to vary the number of layers.
c. Trying to adopt different optimization methods, for example Adam vs. stocahstic gradient descent
d. Trying different pooling functions, average pooling, max pooling, stochastic pooling e. Trying to use different activation functions such as ReLu, Sigmoid etc.
f. Trying to compare different result from using VAE and PCA.