Pikaliov/caption-test
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

belka_gate_fusions: dataset path update to SSD_2_TB

Browse Source
This commit is contained in:
pikaliov
2026-05-18 14:52:41 +03:00
parent b7542b27de
commit b311913034
4 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
conf/gtauav_balanced.gin
View File

@@ -43,7 +43,7 @@ TrainConfigGTAUAV.dss_reembed_every = 1
TrainConfigGTAUAV.use_mutex_sampler = True # legacy flag, kept True unless disabling both samplers TrainConfigGTAUAV.use_mutex_sampler = True # legacy flag, kept True unless disabling both samplers
# ---- Output ---- # ---- Output ----
TrainConfigGTAUAV.output_dir = "out/gtauav/with_text" TrainConfigGTAUAV.output_dir = "out/gtauav/with_text_exp_gate_SRGF"
# ---- Tracking ---- # ---- Tracking ----
TrainConfigGTAUAV.use_wandb = False TrainConfigGTAUAV.use_wandb = False

2
src/models/asymmetric_encoder.py
View File

@@ -261,7 +261,7 @@ class TextFusionMLP(nn.Module):
# --------------------------------------------------------------------------- # ---------------------------------------------------------------------------
# ResidualGateFusin experiment # ResidualGateFusin experiment
from residual_fusions import ResidualGateType, GatedFusionResidual from .residual_fusions import ResidualGateType, GatedFusionResidual
class AsymmetricEncoder(nn.Module): class AsymmetricEncoder(nn.Module):
"""Dual encoder for CVGL with text fusion on both branches. """Dual encoder for CVGL with text fusion on both branches.

3
src/models/dual_encoder.py
View File

@@ -22,7 +22,8 @@ import torch.nn as nn
import torch.nn.functional as F import torch.nn.functional as F
# residual fusions exp # residual fusions exp
from residual_fusions import ResidualGateType, GatedFusionResidual from .residual_fusions import ResidualGateType, GatedFusionResidual
# from residual_fusions import ResidualGateType, GatedFusionResidual
class ProjectionHead(nn.Module): class ProjectionHead(nn.Module):

5
src/training/train_gtauav.py
View File

@@ -58,8 +58,8 @@ from src.models.asymmetric_encoder import (
LOGGER = logging.getLogger("caption_test.train_gtauav") LOGGER = logging.getLogger("caption_test.train_gtauav")
# Default paths. # Default paths.
_RGB_ROOT = "/home/servml/Документы/datasets/GTA-UAV-LR" _RGB_ROOT = "/media/servml/SSD_2_2TB/datasets/cvgl_datasets/GTA-UAV-LR/"
_CAPTION_ROOT = "/home/servml/Документы/datasets/GTA-UAV-LR-captions" _CAPTION_ROOT = "/media/servml/SSD_2_2TB/datasets/cvgl_datasets/GTA-UAV-LR-captions/"
_TRAIN_JSON = "meta/train_80.json" _TRAIN_JSON = "meta/train_80.json"
_TEST_JSON = "meta/test_20.json" _TEST_JSON = "meta/test_20.json"
@@ -100,6 +100,7 @@ class TrainConfigGTAUAV:
# Training. # Training.
resume_from: str | None = None # path to checkpoint for resuming resume_from: str | None = None # path to checkpoint for resuming
# output_dir: str = "out/gtauav/with_text" # output_dir: str = "out/gtauav/with_text"
# ! ----------------- experimental gate outs path -----------------------
output_dir: str = "out/gtauav/with_text_exp_gate_SRGF" output_dir: str = "out/gtauav/with_text_exp_gate_SRGF"
epochs: int = 10 epochs: int = 10
batch_size: int = 8 batch_size: int = 8