Network structure visualization netron
2020-11-29
SSH Tunneling Also known as port forwarding. I.e. setup a network tunnel (a connection for data to flow) from a local point to remote point. Example: ssh username@xx.xx.xx.xx -NL 1234:localhost:1234 1234:localhost:1234 means that any network request you send to port 1234 in your current system will be automatically forwarded to localhost:1234 from the remote system.
2020-11-29
What is tmux? Tmux is a terminal multiplexer You can start a Tmux session and then open multiple windows inside that session. Each window occupies the entire screen and can be split into rectangular panes.
2020-11-29
Open in Google Colab General steps: Set device Set Dataset and DataLoader Define network model Build network model Define loss function and optimizer Define training process Train the model Store/Load weights
2020-11-26
Custom Dataset In order to use our custom dataset, we need to inherit torch.utils.data.Dataset , an abstract class representing a dataset. override __len__ so that len(dataset) returns the size of the dataset.
2020-11-26
import torch import torch.nn as nn import torch.nn.functional as F nn.Module Defines the base class for all neural network We MUST subclass it Example class Net(nn.Module): def __init__(self, in_c, n_classes): super().
2020-11-09
Motivation Saving and loading a general checkpoint model for inference or resuming training can be helpful for picking up where we last left off. When saving a general checkpoint, you must save more than just the model’s state_dict.
2020-11-06
Handling settings for training and valiadtion phase flexibly 💡 Use Python dictionary Phase ('train' or 'val') as key For example: data_transforms = { # For training: data augmentation and normalization 'train': transforms.
2020-11-03
Convolutions Convolutions deliver locality and translation invariance If we want to recognize patterns corresponding to objects, we will likely need to look at how nearby pixels are arranged, and we will be less interested in how pixels that are far from each other appear in combination.
2020-10-27
Dataset of images torchvision module: automatically download the dataset load it as a collection of PyTorch tensors For example, download CIFAR-10 dataset: from torchvision import datasets data_path = '../data-unversioned/p1ch7/' # root directory # Instantiates a dataset for the training data; # TorchVision downloads the data if it is not present.
2020-10-26