friendship ended with earlyoom, now nohang is my best friend
Published:
Stream of Consciousness
This is my stream of consciousness, in which I make available useful notes and thoughts I have which didn't quite make it into blog format.2023
friendship ended with
2022
Siamese network and triplet loss
Published:
Siamese network is an architecture which runs two networks with shared weights (effectively runs the same network twice) on two different inputs simultaneously. It is commonly trained with a contrastive loss such as triplet loss in order to draw together the representations of similar inputs and push apart the representations of contrasting inputs.
Get filepath of Bash activation script
Published:
Use ${BASH_SOURCE[0]} to reference the filepath of a Bash script. Unlike $0, this works if the script is called via bash script.sh or source script.sh.
webcam-mods for Linux background blur & swap
Published:
webcam-mods is the best method I have found for webcam background blur/swap on Linux. I use this for my meetings on Google Meet and Webex.
Beware any vs len
Published:
I fell into the habit of using any() to check if a list is empty. It’s nice because it works for any enumerable, including generators, even if len() is not defined. However, it has a pitfall where if the list is nonempty but contains only falsy values, any() returns False. For this reason, I advise to use len() to check if a list is empty.
Use head -n -0 to get all items in list
Published:
You may know that you can use head -n $n to get the first N lines of a list. But you may not know that you can supply n=-0 to get all items in the list.
Use hard links to replicate log files in a generated directory
Published:
Recently I wanted to write program logs to a file, then copy it to the directory where I store my checkpoints. Because I want to log things before I create the checkpoint directory, I attached my logger to a file in my root directory.
Beware metric auto-reduce with PyTorch Lightning + TorchMetrics
Published:
PyTorch Lightning + TorchMetrics can log metrics per step and per epoch. It also has MetricCollection, which can be used to compute several metrics at once, getting rid of redundant code. Here is how I have it set up:
Print pandas Series as percent
Published:
Use this snippet to print a pd.Series of floats as percentages.
.apply(lambda x: x * 100).apply("{:,.2f}%".format)
Encoder-decoder models
Published:
Encoder decoder is a deep neural network architecture that consists of 2 components:
- Encoder: input -> encoder memory (real-valued vector),
- Decoder: encoder memory -> output. Input is variable length, encoder memory is fixed length.
Print item keys with jq
Published:
I can use jq to print the keys in an array of JSON objects quickly.
jq '.[0] | keys[]' $filename
Neural Network Embeddings
Published:
Embeddings are used to map high-dimensional data to low-dimensional floating-point representation. This may improve the performance because it improves the representation of the input given to the model.