32 lines
963 B
Plaintext
32 lines
963 B
Plaintext
# SOFIA v1 'tiny' variant (~1M params) with text fusion (Text-FiLM mid-level
|
|
# in SAT and UAV heads + AltitudeFiLM in UAV head + GatedFusion late-level).
|
|
|
|
ModelsCommonConfig.backbone = 'sofia_v1'
|
|
ModelsCommonConfig.baseline_mode = True
|
|
ModelsCommonConfig.init_gate = 0.7
|
|
ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
|
|
|
|
# Backbone.
|
|
SOFIAv1ModelsConfig.variant_label = 'tiny'
|
|
SOFIAv1ModelsConfig.in_channels = 3
|
|
SOFIAv1ModelsConfig.input_size = 256
|
|
SOFIAv1ModelsConfig.dcn_variant = 'v2'
|
|
|
|
# Heads.
|
|
SOFIAv1ModelsConfig.d_descriptor = 1024
|
|
SOFIAv1ModelsConfig.return_normalized = False
|
|
|
|
# Altitude-FiLM.
|
|
SOFIAv1ModelsConfig.use_film_altitude = True
|
|
SOFIAv1ModelsConfig.altitude_norm = 500.0
|
|
|
|
# Text-FiLM.
|
|
SOFIAv1ModelsConfig.use_text_film_uav = True
|
|
SOFIAv1ModelsConfig.use_text_film_sat = True
|
|
SOFIAv1ModelsConfig.text_film_dim = 1024
|
|
SOFIAv1ModelsConfig.text_film_hidden = 256
|
|
|
|
# LoRA on DGTRS-CLIP.
|
|
SOFIAv1ModelsConfig.lora_rank = 4
|
|
|