waldo-vision / models

Repository for model development and training
https://waldo.vision
Mozilla Public License 2.0
12 stars 4 forks source link

Pre-Train General FPS Model #6

Open jaredb1011 opened 1 year ago

jaredb1011 commented 1 year ago

Description:

Train the implemented video masked autoencoder model on a dataset of general gameplay clips from first-person shooter (FPS) games.

Requirements:

Acceptance Criteria:

Notes:

Monitor training progress and be prepared to adjust hyperparameters, such as learning rate, batch size, or other factors, to optimize model performance.

Blocked by #5