File size: 1,794 Bytes
8322740 1ba3e62 fcf6aaa 8322740 1ba3e62 fcf6aaa 1ba3e62 fcf6aaa 1ba3e62 fcf6aaa 8322740 1ba3e62 fcf6aaa 1ba3e62 fcf6aaa 1ba3e62 fcf6aaa 8322740 1ba3e62 fcf6aaa 1ba3e62 fcf6aaa 1ba3e62 fcf6aaa 1ba3e62 |
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 |
# svm_vgg_preprocessor.py
import torch
import numpy as np
from torchvision import transforms
from torchvision.models import vgg16
from PIL import Image
class FeatureExtractor:
def __init__(self):
# Load VGG16 with original architecture
self.vgg = vgg16(weights='DEFAULT')
self.vgg.eval()
# Use only convolutional features (matches original code)
self.conv_extractor = self.vgg.features
# Original preprocessing
self.preprocess = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
])
def extract_fc_cnn_features(self, image_path):
"""Matches original FC-CNN feature extraction (conv features)"""
img = Image.open(image_path).convert('RGB')
img_tensor = self.preprocess(img).unsqueeze(0)
with torch.no_grad():
features = self.conv_extractor(img_tensor)
return features.squeeze().numpy().flatten()
def extract_fv_cnn_features(self, image_path):
"""Matches original FV-CNN feature extraction (conv features)"""
img = Image.open(image_path).convert('RGB')
img_tensor = self.preprocess(img).unsqueeze(0)
with torch.no_grad():
features = self.conv_extractor(img_tensor)
return features.squeeze().numpy().flatten()
def extract_combined_features(self, image_path):
"""Original concatenation of identical features"""
fc = self.extract_fc_cnn_features(image_path)
fv = self.extract_fv_cnn_features(image_path)
return np.concatenate((fc, fv)) |