PhenPred / Git / Diff of /README.md

Models:

AlyssaS/

PhenPred

Downloads: 1

Diff of /README.md [f87bf8] .. [f123c6]

Switch to unified view


...
1. Directly run MOSA with the default configurations as described above.

## Instructions for Integrating Disentanglement Learning into MOSA
To incorporate disentanglement learning, two additional terms are included in the loss function, following the Disentangled Inferred Prior Variational Autoencoder (DIP-VAE) approach, as described by [Kumar et al. (2018)](https://arxiv.org/abs/1711.00848):



To use this, update the `hyperparameters.json` file by specifying `dip_vae_type` as either `"i"` or `"ii"` (type ii is recommended), and define the parameters `lambda_d` and `lambda_od` as float values, which control the diagonal and off-diagonal regularization, respectively.

## Pre-trained models
The pre-trained models can be downloaded from the Hugging Face model hub: [MOSA](https://huggingface.co/QuantitativeBiology/MOSA_pretrained)

	a/README.md		b/README.md
	...		...
44	1. Directly run MOSA with the default configurations as described above.	44	1. Directly run MOSA with the default configurations as described above.
45		45
46	## Instructions for Integrating Disentanglement Learning into MOSA	46	## Instructions for Integrating Disentanglement Learning into MOSA
47	To incorporate disentanglement learning, two additional terms are included in the loss function, following the Disentangled Inferred Prior Variational Autoencoder (DIP-VAE) approach, as described by [Kumar et al. (2018)](https://arxiv.org/abs/1711.00848):	47	To incorporate disentanglement learning, two additional terms are included in the loss function, following the Disentangled Inferred Prior Variational Autoencoder (DIP-VAE) approach, as described by [Kumar et al. (2018)](https://arxiv.org/abs/1711.00848):
48		48
49	![DIP-VAE loss term](./figure/dipvae_lossterm.png)
50		49
51	To use this, update the `hyperparameters.json` file by specifying `dip_vae_type` as either `"i"` or `"ii"` (type ii is recommended), and define the parameters `lambda_d` and `lambda_od` as float values, which control the diagonal and off-diagonal regularization, respectively.	50	To use this, update the `hyperparameters.json` file by specifying `dip_vae_type` as either `"i"` or `"ii"` (type ii is recommended), and define the parameters `lambda_d` and `lambda_od` as float values, which control the diagonal and off-diagonal regularization, respectively.
52		51
53	## Pre-trained models	52	## Pre-trained models
54	The pre-trained models can be downloaded from the Hugging Face model hub: [MOSA](https://huggingface.co/QuantitativeBiology/MOSA_pretrained)	53	The pre-trained models can be downloaded from the Hugging Face model hub: [MOSA](https://huggingface.co/QuantitativeBiology/MOSA_pretrained)