Files
torchvision-vibecoding-project/configs/pennfudan_maskrcnn_config.py

34 lines
1.1 KiB
Python

"""
Configuration for training Mask R-CNN on the Penn-Fudan dataset.
"""
from configs.base_config import base_config
# Create a copy of the base configuration
config = base_config.copy()
# Update specific values for this experiment
config.update(
{
# Core configuration
"config_name": "pennfudan_maskrcnn_v1",
"data_root": "data/PennFudanPed",
"num_classes": 2, # background + pedestrian
# Training parameters - modified for memory constraints
"batch_size": 1, # Reduced from 2 to 1 to save memory
"num_epochs": 10,
# Optimizer settings
"lr": 0.002, # Slightly reduced learning rate for smaller batch size
"momentum": 0.9,
"weight_decay": 0.0005,
# Memory optimization settings
"pin_memory": False, # Set to False to reduce memory pressure
"num_workers": 2, # Reduced from 4 to 2
# Device settings
"device": "cuda",
}
)
# Ensure derived paths or settings are consistent if needed
# (Not strictly necessary with this simple structure)