# Model Configuration | |
model: | |
name: "GAIABase" | |
# Image and patch configuration | |
img_size: [1, 480, 1440] # Hardcoded value: time, height, width | |
patch_size: [1, 30, 30] # Hardcoded value: time_patch, height_patch, width_patch | |
in_chans: 1 # Hardcoded: Number of input channels | |
# Encoder configuration | |
encoder_embed_dim: 912 # Hardcoded based on original computation | |
encoder_depth: 24 | |
encoder_num_heads: 16 | |
# Decoder configuration | |
decoder_embed_dim: 512 | |
decoder_depth: 8 | |
decoder_num_heads: 16 | |
# Common configuration | |
mlp_ratio: 4.0 | |
norm_pix_loss: false | |
drop_channels_rate: 0 | |
# DINO specific configuration | |
adjacent_masking: false | |
norm_last_layer: true | |
dino_head_dim: 1024 | |
warmup_teacher_temp: 0.04 | |
teacher_temp: 0.04 | |
warmup_teacher_temp_epochs: 1 | |
student_temp: 0.1 | |
center_momentum: 0.9 | |
momentum_teacher: 0.996 | |
# Masking configuration | |
mask_ratio: 0.75 | |
training: | |
epochs: 100 | |
val_step: 0 | |
optimizer: | |
learning_rate: 1.5e-4 | |
scheduler: | |
type: "CosineAnnealingLR" | |
warmup_steps: 500 | |
total_steps: 10000 | |
eta_min: 1.0e-6 | |
last_step: -1 |