claude_refactor_v3: De-duplicate gin-configs, + "in/config_files" with common and cpecific experiment-presets gins

in/config_files/gtauav_balanced/models.gin

@@ -0,0 +1,12 @@
+# DINOv3 shared encoder + MONA-12 + DGTRS-CLIP with text.
+ModelsCommonConfig.backbone = 'dinov3'
+ModelsCommonConfig.baseline_mode = False
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+DINOv3ModelsConfig.dino_web_path = 'nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth'
+DINOv3ModelsConfig.dino_sat_path = 'nn_models/DINO_SAT/model.safetensors'
+DINOv3ModelsConfig.shared_encoder = True
+DINOv3ModelsConfig.mona_bottleneck = 64
+DINOv3ModelsConfig.mona_last_n_blocks = 12
+DINOv3ModelsConfig.lora_rank = 4

in/config_files/gtauav_balanced/pipeline.gin

@@ -0,0 +1,14 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/with_text'
+PipelineConfig.resume_from = None

in/config_files/gtauav_balanced_asym/models.gin

@@ -0,0 +1,11 @@
+ModelsCommonConfig.backbone = 'dinov3'
+ModelsCommonConfig.baseline_mode = False
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+DINOv3ModelsConfig.dino_web_path = 'nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth'
+DINOv3ModelsConfig.dino_sat_path = 'nn_models/DINO_SAT/model.safetensors'
+DINOv3ModelsConfig.shared_encoder = False            
+DINOv3ModelsConfig.mona_bottleneck = 64
+DINOv3ModelsConfig.mona_last_n_blocks = 24           
+DINOv3ModelsConfig.lora_rank = 4

in/config_files/gtauav_balanced_asym/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/balanced_asym'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_balanced_sofia/models.gin

@@ -0,0 +1,91 @@
+# SOFIA v7.1 Tiny preset (~5M params) with text fusion (Text-FiLM mid-level
+# in SAT and UAV heads + GatedFusion late-level on descriptors).
+#
+# Tiny-specific notes:
+#   - num_heads_s3/s4 = 4 (channels 176/224 not divisible by 8)
+#   - mamba_headdim = 16 (channels not divisible by default 64)
+#   - mamba_variant = 'mamba1' (Mamba-2 torch fallback bug for these dims)
+#   - d_descriptor = 1024 (override from preset M default 512)
+#   - text fusion enabled (override from preset M default disabled)
+
+ModelsCommonConfig.backbone = 'sofia_v71'
+ModelsCommonConfig.baseline_mode = False
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+# Variant label (informational).
+SOFIAv71ModelsConfig.variant_label = 'Tiny'
+
+# Input.
+SOFIAv71ModelsConfig.input_size = 256
+SOFIAv71ModelsConfig.in_channels = 3
+
+# Stem (Tiny dims).
+SOFIAv71ModelsConfig.stem_mid = 16
+SOFIAv71ModelsConfig.stem_out = 32
+
+# Backbone dimensions (Tiny).
+SOFIAv71ModelsConfig.embed_dims = [48, 96, 176, 224]
+SOFIAv71ModelsConfig.depths = [2, 3, 4, 2]
+
+# Stage 1-2 block params (default).
+SOFIAv71ModelsConfig.mbconv_expand = 4
+SOFIAv71ModelsConfig.se_ratio = 16
+SOFIAv71ModelsConfig.strip_kernel_s1 = 7
+SOFIAv71ModelsConfig.strip_kernel_s2 = 5
+SOFIAv71ModelsConfig.mix_kernels = [3, 5, 7]
+SOFIAv71ModelsConfig.use_dcn_strip = True
+
+# Stage 3-4 (MambaVision). Tiny: mamba1 to bypass torch fallback bug.
+SOFIAv71ModelsConfig.mamba_d_state = 16
+SOFIAv71ModelsConfig.mamba_dt_rank = None
+SOFIAv71ModelsConfig.mamba_backend = 'auto'
+SOFIAv71ModelsConfig.mamba_variant = 'mamba1'
+
+# Mamba-2 tunables (used when mamba_variant='mamba2'; Tiny would need
+# headdim=16 because 176 % 64 != 0 and 224 % 64 != 0).
+SOFIAv71ModelsConfig.mamba_d_state_mamba2 = 64
+SOFIAv71ModelsConfig.mamba_headdim = 16
+SOFIAv71ModelsConfig.mamba_expand = 2
+SOFIAv71ModelsConfig.mamba_d_conv = 4
+SOFIAv71ModelsConfig.mamba_n_directions = 2
+
+# Heads / attention (Tiny: heads=4).
+SOFIAv71ModelsConfig.num_heads_s3 = 4
+SOFIAv71ModelsConfig.num_heads_s4 = 4
+SOFIAv71ModelsConfig.use_strip_branch_s3 = True
+SOFIAv71ModelsConfig.use_strip_branch_s4 = False
+SOFIAv71ModelsConfig.ffn_expand = 4
+
+# EVSS bridge (off by default).
+SOFIAv71ModelsConfig.use_evss_bridge = False
+SOFIAv71ModelsConfig.evss_bridge_locations = ['pre_stage3']
+
+# Neck (Tiny).
+SOFIAv71ModelsConfig.neck_channels = 128
+
+# CVGL Head.
+SOFIAv71ModelsConfig.d_descriptor = 1024
+SOFIAv71ModelsConfig.use_asymmetric_heads = True
+SOFIAv71ModelsConfig.chp_rings = 8
+SOFIAv71ModelsConfig.chp_angles = 16
+SOFIAv71ModelsConfig.chp_harmonics = 4
+SOFIAv71ModelsConfig.use_film_altitude = True
+SOFIAv71ModelsConfig.altitude_norm = 500.0
+SOFIAv71ModelsConfig.ring_count = 4
+SOFIAv71ModelsConfig.use_ring_aux = True
+
+# Text fusion enabled.
+SOFIAv71ModelsConfig.return_normalized = True
+SOFIAv71ModelsConfig.use_text_film_sat = True
+SOFIAv71ModelsConfig.use_text_film_uav = True
+SOFIAv71ModelsConfig.text_film_dim = 1024
+SOFIAv71ModelsConfig.text_film_hidden = 256
+
+# Sharing / KD / deploy.
+SOFIAv71ModelsConfig.share_stages_1_2 = True
+SOFIAv71ModelsConfig.enable_kd_taps = True
+SOFIAv71ModelsConfig.precision = 'fp16'
+
+# LoRA.
+SOFIAv71ModelsConfig.lora_rank = 4

in/config_files/gtauav_balanced_sofia/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/with_text_sofia'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_balanced_sofia_v1/models.gin

@@ -0,0 +1,30 @@
+# 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 = False
+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

in/config_files/gtauav_balanced_sofia_v1/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/with_text_sofia_v1'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_balanced_stripnet/models.gin

@@ -0,0 +1,11 @@
+# StripNet small backbone (frozen) + Conv-MONA on last 2 stages.
+ModelsCommonConfig.backbone = 'stripnet'
+ModelsCommonConfig.baseline_mode = False
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+StripNetModelsConfig.stripnet_path = 'nn_models/STRIPNET/stripnet_s.pth'
+StripNetModelsConfig.stripnet_freeze = True
+StripNetModelsConfig.stripnet_mona_last_n_stages = 2
+StripNetModelsConfig.stripnet_backbone_lr_factor = 0.1
+StripNetModelsConfig.lora_rank = 4

in/config_files/gtauav_balanced_stripnet/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/balanced_stripnet'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_balanced_stripnet_unfrozen/models.gin

@@ -0,0 +1,11 @@
+# StripNet small backbone (frozen) + Conv-MONA on last 2 stages.
+ModelsCommonConfig.backbone = 'stripnet'
+ModelsCommonConfig.baseline_mode = False
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+StripNetModelsConfig.stripnet_path = 'nn_models/STRIPNET/stripnet_s.pth'
+StripNetModelsConfig.stripnet_freeze = False
+StripNetModelsConfig.stripnet_mona_last_n_stages = 2
+StripNetModelsConfig.stripnet_backbone_lr_factor = 0.1
+StripNetModelsConfig.lora_rank = 4

in/config_files/gtauav_balanced_stripnet_unfrozen/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/balanced_stripnet_unfrozen'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_baseline/models.gin

@@ -0,0 +1,12 @@
+# DINOv3 shared encoder + MONA-12 + DGTRS-CLIP with text.
+ModelsCommonConfig.backbone = 'dinov3'
+ModelsCommonConfig.baseline_mode = True
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+DINOv3ModelsConfig.dino_web_path = 'nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth'
+DINOv3ModelsConfig.dino_sat_path = 'nn_models/DINO_SAT/model.safetensors'
+DINOv3ModelsConfig.shared_encoder = True
+DINOv3ModelsConfig.mona_bottleneck = 64
+DINOv3ModelsConfig.mona_last_n_blocks = 12
+DINOv3ModelsConfig.lora_rank = 4

in/config_files/gtauav_baseline/pipeline.gin

@@ -0,0 +1,14 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/baseline_inbatch'
+PipelineConfig.resume_from = None

in/config_files/gtauav_baseline_asym/models.gin

@@ -0,0 +1,12 @@
+# DINOv3 shared encoder + MONA-12 + DGTRS-CLIP with text.
+ModelsCommonConfig.backbone = 'dinov3'
+ModelsCommonConfig.baseline_mode = True
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+DINOv3ModelsConfig.dino_web_path = 'nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth'
+DINOv3ModelsConfig.dino_sat_path = 'nn_models/DINO_SAT/model.safetensors'
+DINOv3ModelsConfig.shared_encoder = False
+DINOv3ModelsConfig.mona_bottleneck = 64
+DINOv3ModelsConfig.mona_last_n_blocks = 24
+DINOv3ModelsConfig.lora_rank = 4

in/config_files/gtauav_baseline_asym/pipeline.gin

@@ -0,0 +1,14 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/baseline_asym'
+PipelineConfig.resume_from = None

in/config_files/gtauav_baseline_sofia/models.gin

@@ -0,0 +1,92 @@
+# SOFIA v7.1 Tiny preset (~5M params) with text fusion (Text-FiLM mid-level
+# in SAT and UAV heads + GatedFusion late-level on descriptors).
+#
+# Tiny-specific notes:
+#   - num_heads_s3/s4 = 4 (channels 176/224 not divisible by 8)
+#   - mamba_headdim = 16 (channels not divisible by default 64)
+#   - mamba_variant = 'mamba1' (Mamba-2 torch fallback bug for these dims)
+#   - d_descriptor = 1024 (override from preset M default 512)
+#   - text fusion enabled (override from preset M default disabled)
+
+ModelsCommonConfig.backbone = 'sofia_v71'
+ModelsCommonConfig.baseline_mode = True
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+# Variant label (informational).
+SOFIAv71ModelsConfig.variant_label = 'Tiny'
+
+# Input.
+SOFIAv71ModelsConfig.input_size = 256
+SOFIAv71ModelsConfig.in_channels = 3
+
+# Stem (Tiny dims).
+SOFIAv71ModelsConfig.stem_mid = 16
+SOFIAv71ModelsConfig.stem_out = 32
+
+# Backbone dimensions (Tiny).
+SOFIAv71ModelsConfig.embed_dims = [48, 96, 176, 224]
+SOFIAv71ModelsConfig.depths = [2, 3, 4, 2]
+
+# Stage 1-2 block params (default).
+SOFIAv71ModelsConfig.mbconv_expand = 4
+SOFIAv71ModelsConfig.se_ratio = 16
+SOFIAv71ModelsConfig.strip_kernel_s1 = 7
+SOFIAv71ModelsConfig.strip_kernel_s2 = 5
+SOFIAv71ModelsConfig.mix_kernels = [3, 5, 7]
+SOFIAv71ModelsConfig.use_dcn_strip = True
+
+# Stage 3-4 (MambaVision). Tiny: mamba1 to bypass torch fallback bug.
+SOFIAv71ModelsConfig.mamba_d_state = 16
+SOFIAv71ModelsConfig.mamba_dt_rank = None
+SOFIAv71ModelsConfig.mamba_backend = 'auto'
+SOFIAv71ModelsConfig.mamba_variant = 'mamba1'
+
+# Mamba-2 tunables (used when mamba_variant='mamba2'; Tiny would need
+# headdim=16 because 176 % 64 != 0 and 224 % 64 != 0).
+SOFIAv71ModelsConfig.mamba_d_state_mamba2 = 64
+SOFIAv71ModelsConfig.mamba_headdim = 16
+SOFIAv71ModelsConfig.mamba_expand = 2
+SOFIAv71ModelsConfig.mamba_d_conv = 4
+SOFIAv71ModelsConfig.mamba_n_directions = 2
+
+# Heads / attention (Tiny: heads=4).
+SOFIAv71ModelsConfig.num_heads_s3 = 4
+SOFIAv71ModelsConfig.num_heads_s4 = 4
+SOFIAv71ModelsConfig.use_strip_branch_s3 = True
+SOFIAv71ModelsConfig.use_strip_branch_s4 = False
+SOFIAv71ModelsConfig.ffn_expand = 4
+
+# EVSS bridge (off by default).
+SOFIAv71ModelsConfig.use_evss_bridge = False
+SOFIAv71ModelsConfig.evss_bridge_locations = ['pre_stage3']
+
+# Neck (Tiny).
+SOFIAv71ModelsConfig.neck_channels = 128
+
+# CVGL Head.
+SOFIAv71ModelsConfig.d_descriptor = 1024
+SOFIAv71ModelsConfig.use_asymmetric_heads = True
+SOFIAv71ModelsConfig.chp_rings = 8
+SOFIAv71ModelsConfig.chp_angles = 16
+SOFIAv71ModelsConfig.chp_harmonics = 4
+SOFIAv71ModelsConfig.use_film_altitude = True
+SOFIAv71ModelsConfig.altitude_norm = 500.0
+SOFIAv71ModelsConfig.ring_count = 4
+SOFIAv71ModelsConfig.use_ring_aux = True
+
+# Text fusion enabled.
+SOFIAv71ModelsConfig.return_normalized = True
+SOFIAv71ModelsConfig.use_text_film_sat = True
+SOFIAv71ModelsConfig.use_text_film_uav = True
+SOFIAv71ModelsConfig.text_film_dim = 1024
+SOFIAv71ModelsConfig.text_film_hidden = 256
+
+# Sharing / KD / deploy.
+SOFIAv71ModelsConfig.share_stages_1_2 = True
+SOFIAv71ModelsConfig.enable_kd_taps = True
+SOFIAv71ModelsConfig.precision = 'fp16'
+
+# LoRA.
+SOFIAv71ModelsConfig.lora_rank = 4
+

in/config_files/gtauav_baseline_sofia/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/baseline_sofia'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_baseline_sofia_v1/models.gin

@@ -0,0 +1,31 @@
+# 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
+

in/config_files/gtauav_baseline_sofia_v1/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/baseline_sofia_v1'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_baseline_stripnet/models.gin

@@ -0,0 +1,12 @@
+# StripNet small backbone (frozen) + Conv-MONA on last 2 stages.
+ModelsCommonConfig.backbone = 'stripnet'
+ModelsCommonConfig.baseline_mode = True
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+StripNetModelsConfig.stripnet_path = 'nn_models/STRIPNET/stripnet_s.pth'
+StripNetModelsConfig.stripnet_freeze = True
+StripNetModelsConfig.stripnet_mona_last_n_stages = 2
+StripNetModelsConfig.stripnet_backbone_lr_factor = 0.1
+StripNetModelsConfig.lora_rank = 4
+

in/config_files/gtauav_baseline_stripnet/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/baseline_stripnet'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_baseline_stripnet_unfrozen/models.gin

@@ -0,0 +1,11 @@
+# StripNet small backbone (unfrozen) + Conv-MONA on last 2 stages.
+ModelsCommonConfig.backbone = 'stripnet'
+ModelsCommonConfig.baseline_mode = True
+ModelsCommonConfig.init_gate = 0.7
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+StripNetModelsConfig.stripnet_path = 'nn_models/STRIPNET/stripnet_s.pth'
+StripNetModelsConfig.stripnet_freeze = False
+StripNetModelsConfig.stripnet_mona_last_n_stages = 2
+StripNetModelsConfig.stripnet_backbone_lr_factor = 0.1
+StripNetModelsConfig.lora_rank = 4

in/config_files/gtauav_baseline_stripnet_unfrozen/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/baseline_stripnet_unfrozen'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_image_heavy/models.gin

@@ -0,0 +1,13 @@
+# DINOv3 shared encoder + MONA-12 + DGTRS-CLIP with text.
+ModelsCommonConfig.backbone = 'dinov3'
+ModelsCommonConfig.baseline_mode = False
+ModelsCommonConfig.init_gate = 0.9
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+DINOv3ModelsConfig.dino_web_path = 'nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth'
+DINOv3ModelsConfig.dino_sat_path = 'nn_models/DINO_SAT/model.safetensors'
+DINOv3ModelsConfig.shared_encoder = True
+DINOv3ModelsConfig.mona_bottleneck = 64
+DINOv3ModelsConfig.mona_last_n_blocks = 12
+DINOv3ModelsConfig.lora_rank = 4
+

in/config_files/gtauav_image_heavy/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/image_heavy'
+PipelineConfig.resume_from = None
+

in/config_files/gtauav_text_heavy/models.gin

@@ -0,0 +1,13 @@
+# DINOv3 shared encoder + MONA-12 + DGTRS-CLIP with text.
+ModelsCommonConfig.backbone = 'dinov3'
+ModelsCommonConfig.baseline_mode = False
+ModelsCommonConfig.init_gate = 0.3
+ModelsCommonConfig.lrsclip_path = 'nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt'
+
+DINOv3ModelsConfig.dino_web_path = 'nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth'
+DINOv3ModelsConfig.dino_sat_path = 'nn_models/DINO_SAT/model.safetensors'
+DINOv3ModelsConfig.shared_encoder = True
+DINOv3ModelsConfig.mona_bottleneck = 64
+DINOv3ModelsConfig.mona_last_n_blocks = 12
+DINOv3ModelsConfig.lora_rank = 4
+

in/config_files/gtauav_text_heavy/pipeline.gin

@@ -0,0 +1,15 @@
+# Pipeline: GTA-UAV-LR with text captions, servml workstation paths.
+PipelineConfig.train_json = 'meta/train_80.json'
+PipelineConfig.test_json = 'meta/test_20.json'
+PipelineConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PipelineConfig.caption_root = '/home/servml/Документы/datasets/GTA-UAV-LR-captions'
+PipelineConfig.filter_meta = 'meta/seg_filter.json'
+
+PipelineConfig.epochs = 10
+PipelineConfig.warmup_epochs = 2
+PipelineConfig.eval_every = 1
+PipelineConfig.seed = 42
+
+PipelineConfig.output_dir = 'out/gtauav/text_heavy'
+PipelineConfig.resume_from = None
+

in/config_files/hardware.gin

@@ -1 +0,0 @@
-

in/config_files/hardware_default.gin

@@ -0,0 +1,9 @@
+# RTX 4090 profile, shared encoder (DINOv3).
+HardwareConfig.device = 'cuda'
+HardwareConfig.batch_size = 8
+HardwareConfig.grad_accum_steps = 8
+HardwareConfig.num_workers = 4
+HardwareConfig.use_amp = True
+HardwareConfig.gradient_checkpointing = True
+HardwareConfig.reserve_gb = 2.0
+HardwareConfig.total_vram_gb = 24.0

in/config_files/hardware_no_gradckpt.gin

@@ -0,0 +1,10 @@
+# SOFIA v7.1 from-scratch — keep activations live (no gradient checkpointing).
+HardwareConfig.device = 'cuda'
+HardwareConfig.batch_size = 8
+HardwareConfig.grad_accum_steps = 8
+HardwareConfig.num_workers = 4
+HardwareConfig.use_amp = True
+HardwareConfig.gradient_checkpointing = False
+HardwareConfig.reserve_gb = 2.0
+HardwareConfig.total_vram_gb = 24.0
+

in/config_files/models.gin

@@ -1 +0,0 @@
-

in/config_files/pipeline.gin

@@ -1 +0,0 @@
-

in/config_files/preprocess/preprocess.gin

@@ -0,0 +1,20 @@
+# Preprocessing config used by scripts/make_split.py and
+# scripts/filter_segmentation.py. Independent from training pipeline.
+
+# Inputs.
+PreprocessConfig.rgb_root = '/home/servml/Документы/datasets/GTA-UAV-LR'
+PreprocessConfig.segm_root = '/home/servml/Документы/datasets/GTA-UAV-LR-aug/segm'
+
+# make_split.py — 80/20 split with seed=42.
+PreprocessConfig.split_ratio = 0.8
+PreprocessConfig.split_seed = 42
+PreprocessConfig.split_input_train = 'cross-area-drone2sate-train.json'
+PreprocessConfig.split_input_test = 'cross-area-drone2sate-test.json'
+PreprocessConfig.split_output_dir = 'meta'
+PreprocessConfig.split_output_train = 'train_80.json'
+PreprocessConfig.split_output_test = 'test_20.json'
+
+# filter_segmentation.py — exclude images with >=90% background+water.
+PreprocessConfig.seg_threshold = 0.90
+PreprocessConfig.seg_exclude_classes = [0, 4]
+PreprocessConfig.seg_filter_output = 'meta/seg_filter.json'

in/config_files/tracking.gin

@@ -1 +1,16 @@
+# Default tracking: TensorBoard on, W&B off, no Grad-CAM, no profiler.
+TrackingConfig.use_wandb = False
+TrackingConfig.use_tb = True
+TrackingConfig.wandb_project = 'caption-test-gtauav'
+TrackingConfig.wandb_run_name = None
+TrackingConfig.wandb_entity = None
+
+TrackingConfig.log_grad_norms = True
+TrackingConfig.use_gradcam = False
+TrackingConfig.gradcam_every = 5
+TrackingConfig.gradcam_samples = 8
+
+TrackingConfig.use_profiler = False
+TrackingConfig.profiler_warmup = 3
+TrackingConfig.profiler_active = 5
 

in/config_files/training.gin

@@ -1 +1,31 @@
+# Loss + optimizer + sampler — symmetric InfoNCE, AdamW, mutex sampler.
+TrainingConfig.loss_type = 'symmetric'
+TrainingConfig.tau_init = 0.07
+TrainingConfig.tau_min = 0.01
+TrainingConfig.tau_max = 0.1
+TrainingConfig.learnable_temperature = True
+TrainingConfig.label_smoothing = 0.1
 
+TrainingConfig.tau_final = 0.01
+TrainingConfig.weight_q2g = 0.6
+TrainingConfig.weight_g2q = 0.4
+TrainingConfig.hard_mining_k = 0
+TrainingConfig.neg_bank_size = 0
+
+# WeightedInfoNCE-only (unused when loss_type='symmetric').
+TrainingConfig.weighted_loss_k = 5.0
+
+TrainingConfig.learning_rate = 1e-4
+TrainingConfig.text_lr_factor = 0.1
+TrainingConfig.weight_decay = 1e-4
+TrainingConfig.grad_clip = 1.0
+
+TrainingConfig.sampler_type = 'mutex'
+TrainingConfig.dss_warmup_epochs = 1
+TrainingConfig.dss_reembed_every = 1
+TrainingConfig.dss_knn_device = 'cuda'
+TrainingConfig.dss_use_lsh = False
+TrainingConfig.dss_lsh_num_tables = 8
+TrainingConfig.dss_lsh_num_bits = 14
+TrainingConfig.dss_cache_dir = None
+TrainingConfig.use_mutex_sampler = True