claude_refactor_v3: Added .py-confs and all presets (nx5 .gin files). TODO: common gins-mapping and prepare to next step

presets/gtauav_balanced_sofia_v1/hardware.gin

@@ -1 +1,8 @@
-
+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

presets/gtauav_balanced_sofia_v1/models.gin

@@ -1 +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

presets/gtauav_balanced_sofia_v1/pipeline.gin

@@ -1 +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
 

presets/gtauav_balanced_sofia_v1/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
 

presets/gtauav_balanced_sofia_v1/training.gin

@@ -1 +1,32 @@
+# 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