File size: 4,160 Bytes
37fbec9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | # ─────────────────────────────────────────────────────────────────────────────
# config.yaml — Central configuration for the Chest X-Ray ViT project
# Optimized for RTX 3050 Laptop GPU (4 GB VRAM)
# ─────────────────────────────────────────────────────────────────────────────
# ── Paths ─────────────────────────────────────────────────────────────────────
paths:
data_root: "./data/raw" # Root where Kaggle data is extracted
images_dir: "./data/raw/images" # Folder containing all .png X-rays
labels_csv: "./data/raw/Data_Entry_2017.csv"
train_list: "./data/raw/train_val_list.txt"
test_list: "./data/raw/test_list.txt"
checkpoints_dir: "./checkpoints"
results_dir: "./results"
mlflow_dir: "./experiments/mlflow"
# ── Dataset ───────────────────────────────────────────────────────────────────
dataset:
image_size: 224 # ViT-Base-16 expects 224×224
# Use a fraction of training data for quick iteration on RTX 3050
# Set to 1.0 for full training, 0.2 for fast smoke-test
train_fraction: 1.0
val_split: 0.1 # 10% of train_val_list used as validation
num_workers: 0 # 0 = safe on Windows; increase if Linux
pin_memory: true
# ── Model ─────────────────────────────────────────────────────────────────────
model:
name: "google/vit-base-patch16-224-in21k" # Pre-trained on ImageNet-21k
num_classes: 14
dropout: 0.1
gradient_checkpointing: true # Saves ~30% VRAM on RTX 3050
# ── Training ──────────────────────────────────────────────────────────────────
training:
num_epochs: 10 # Conservative for RTX 3050; increase if time allows
batch_size: 16 # Fits in 4 GB VRAM with grad-checkpointing
gradient_accumulation_steps: 2 # Effective batch = 32
learning_rate: 2.0e-5 # Typical fine-tune LR for ViT
weight_decay: 0.01
warmup_ratio: 0.05 # 5% of total steps for LR warmup
max_grad_norm: 1.0 # Gradient clipping
mixed_precision: true # fp16 — mandatory for 4 GB VRAM
save_best_only: true
log_interval: 50 # Log every N optimizer steps
# ── Diseases (NIH ChestX-ray14 label set) ─────────────────────────────────────
diseases:
- "Atelectasis"
- "Cardiomegaly"
- "Effusion"
- "Infiltration"
- "Mass"
- "Nodule"
- "Pneumonia"
- "Pneumothorax"
- "Consolidation"
- "Edema"
- "Emphysema"
- "Fibrosis"
- "Pleural_Thickening"
- "Hernia"
# ── MLflow ────────────────────────────────────────────────────────────────────
mlflow:
experiment_name: "chest-xray-vit"
run_name: "vit-base16-clahe-v1"
# ── Inference / Demo ──────────────────────────────────────────────────────────
inference:
threshold: 0.5 # Sigmoid threshold for positive prediction
gradio_port: 7860
gradio_share: false # Set true to get public URL (ngrok)
|