[cv231n] Lecture 8 | Deep Learning Software

Lecture 8 | Deep Learning Software

---

 Deep Learning Software

GPUs are really good for parallel things where you need to do many things at the same time.

the dot product of two vectors

CUDA can process deep learning in a efficiencies way. (cuDNN libraries)

GPU vs CPU in practice

Deeplearning framework

The point of deep learning frameworks

Numpy cs PyTorch

Numpy bad:

• can't run on GPU
• Have to compute our own gradients
   

 

Tensorflow

 Problem: copying weights between CPU / GPU each step

 

 Problem: loss not going down! Assign calls not actually being executed!

TensorFlow: Loss
 

TensorFlow: Layers

Keras: High-Level Wrapper
 

TF package

Keras (https://keras.io/)
tf.keras (https://www.tensorflow.org/api_docs/python/tf/keras)
tf.layers (https://www.tensorflow.org/api_docs/python/tf/layers)
tf.estimator (https://www.tensorflow.org/api_docs/python/tf/estimator)
tf.contrib.estimator (https://www.tensorflow.org/api_docs/python/tf/contrib/estimator)
tf.contrib.layers (https://www.tensorflow.org/api_docs/python/tf/contrib/layers)
tf.contrib.slim (https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/slim)
tf.contrib.learn (https://www.tensorflow.org/api_docs/python/tf/contrib/learn)
TFLearn (http://tflearn.org/)
TensorLayer (http://tensorlayer.readthedocs.io/en/latest/)

---

PyTorch

PyTorch: Tensors

 PyTorch: Autograd

PyTorch: New Autograd Functions

 

PyTorch: nn

PyTorch: opti

PyTorch: nn Define new Modules
 

PyTorch: DataLoaders

PyTorch: Pretrained Models

PyTorch: Visdom

PyTorch: Dynamic Computation Graphs

---

Static vs Dynamic

Static vs Dynamic: Graphs

Static vs Dynamic: Conditional

Static vs Dynamic: Loops

Dynamic Graph Applications

PyTorch vs TensorFlow, Static vs Dynamic

---

Caffe