File size: 5,955 Bytes
7902c8d | 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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
# ══════════════════════════════════════════════════════════════════════════════
# PYTORCH — Transforms & DataLoaders
# ══════════════════════════════════════════════════════════════════════════════
def get_pytorch_transforms(img_size: int = 150):
"""
Retourne (train_transform, val_transform).
Augmentation scène-aware pour le dataset Intel (6 classes naturelles RGB).
"""
from torchvision import transforms
# Statistiques ImageNet — optimal pour images naturelles RGB 3 canaux
MEAN = [0.485, 0.456, 0.406]
STD = [0.229, 0.224, 0.225]
train_transform = transforms.Compose([
transforms.Resize((img_size, img_size)),
transforms.RandomHorizontalFlip(p=0.5),
transforms.RandomVerticalFlip(p=0.1),
transforms.RandomRotation(degrees=40),
transforms.ColorJitter(
brightness=0.3, contrast=0.2, saturation=0.1, hue=0.05
),
transforms.RandomGrayscale(p=0.05),
transforms.ToTensor(),
transforms.Normalize(MEAN, STD), # ← normalisation ici, pas dans le modèle
transforms.RandomErasing(p=0.15, scale=(0.02, 0.15)),
])
val_transform = transforms.Compose([
transforms.Resize((img_size, img_size)),
transforms.ToTensor(),
transforms.Normalize(MEAN, STD), # ← même normalisation en val/test
])
return train_transform, val_transform
def get_pytorch_loaders(
train_dir: str,
test_dir: str,
img_size: int = 150,
batch_size: int = 64,
):
from torch.utils.data import DataLoader
from torchvision import datasets
train_tf, val_tf = get_pytorch_transforms(img_size)
train_loader = DataLoader(
datasets.ImageFolder(train_dir, transform=train_tf),
batch_size=batch_size, shuffle=True,
num_workers=2, pin_memory=True,
)
test_loader = DataLoader(
datasets.ImageFolder(test_dir, transform=val_tf),
batch_size=batch_size, shuffle=False,
num_workers=2, pin_memory=True,
)
return train_loader, test_loader
# ══════════════════════════════════════════════════════════════════════════════
# TENSORFLOW — Dataset pipeline
# ══════════════════════════════════════════════════════════════════════════════
def get_tf_datasets(
train_dir: str,
test_dir: str,
img_size: int = 228,
batch_size: int = 64,
):
import tensorflow as tf
# Same preprocessing as in the notebook
norm_layer = tf.keras.layers.Rescaling(1.0 / 255.0)
# ── Raw loading ──────────────────────────────────────────────────────────
train_ds = tf.keras.utils.image_dataset_from_directory(
train_dir,
seed=123,
image_size=(img_size, img_size),
batch_size=batch_size,
shuffle=True,
label_mode="int",
)
test_ds = tf.keras.utils.image_dataset_from_directory(
test_dir,
seed=123,
image_size=(img_size, img_size),
batch_size=batch_size,
shuffle=False,
label_mode="int",
)
# ── Normalization only ───────────────────────────────────────────────────
train_ds = train_ds.map(
lambda x, y: (norm_layer(x), y),
num_parallel_calls=tf.data.AUTOTUNE
)
test_ds = test_ds.map(
lambda x, y: (norm_layer(x), y),
num_parallel_calls=tf.data.AUTOTUNE
)
# ── Performance ──────────────────────────────────────────────────────────
train_ds = train_ds.prefetch(tf.data.AUTOTUNE)
test_ds = test_ds.prefetch(tf.data.AUTOTUNE)
return train_ds, test_ds
# ══════════════════════════════════════════════════════════════════════════════
# INFÉRENCE — Preprocessing image unique (Flask / production)
# ══════════════════════════════════════════════════════════════════════════════
def preprocess_image_pytorch(pil_img, img_size: int = 150):
"""Prépare une image PIL pour l'inférence PyTorch. Retourne (1,3,H,W)."""
import torch
from torchvision import transforms
tf = transforms.Compose([
transforms.Resize((img_size, img_size)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
return tf(pil_img).unsqueeze(0)
def preprocess_image_tf(pil_img, img_size: int = 150):
"""
Prépare une image PIL pour l'inférence TensorFlow. Retourne (1,H,W,3).
Normalisation identique au pipeline val/test : ÷255 → [0,1].
"""
import numpy as np
arr = np.array(pil_img.resize((img_size, img_size)), dtype=np.float32)
arr = arr / 255.0 # ← même normalisation que normalize_only()
return np.expand_dims(arr, 0) # (1, H, W, 3)
|