i tried to create a python script for detect the object in a picture and return the similar images, but it return always an error:
TypeError: only integer scalar arrays can be converted to a scalar index
the ids : is the matrix returned after the detection; and it returned perfectly
but the problem is only in the last line: scores = [img_paths[id] for id in ids].
My code :
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.vgg16 import VGG16, preprocess_input
from tensorflow.keras.models import Model
import numpy as np
from PIL import Image
#from feature_extractor import FeatureExtractor
from datetime import datetime
from flask import Flask, request, render_template
from pathlib import Path
from keras.optimizers import Adam
from tensorflow.keras.layers import Dropout, Dense, Activation, Flatten
class FeatureExtractor:
def __init__(self):
input_shape = (224, 224, 3)
base_model = VGG16(weights='imagenet', include_top=False, input_shape=input_shape)
for layer in base_model.layers:
layer.trainable = False
last = base_model.layers[-1].output
x = Flatten()(last)
x = Dense(1000, activation='relu', name='fc1')(x)
x = Dropout(0.3)(x)
x = Dense(10, activation='softmax', name='predictions')(x)
model = Model(base_model.input, x)
model.compile(optimizer=Adam(lr=0.001),
loss = 'categorical_crossentropy',metrics=['accuracy'])
self.model = Model(inputs=base_model.input, outputs=base_model.layers[-1].output)
def extract(self, img):
"""
Extract a deep feature from an input image
Args:
img: from PIL.Image.open(path) or tensorflow.keras.preprocessing.image.load_img(path)
Returns:
feature (np.ndarray): deep feature with the shape=(4096, )
"""
img = img.resize((224, 224)) # VGG must take a 224x224 img as an input
img = img.convert('RGB') # Make sure img is color
x = image.img_to_array(img) # To np.array. Height x Width x Channel. dtype=float32
x = np.expand_dims(x, axis=0) # (H, W, C)->(1, H, W, C), where the first elem is the number of img
x = preprocess_input(x) # Subtracting avg values for each pixel
feature = self.model.predict(x)[0] # (1, 4096) -> (4096, )
return feature / np.linalg.norm(feature) # Normalize
path = "/home/virtuag/www/storage/searchSCB.jpg"
img = Image.open(path)
app = Flask(__name__)
fe = FeatureExtractor()
features = []
img_paths = []
for feature_path in Path("/home/virtuag/www/storage/images_article").glob("*.npy"):
features.append(np.load(feature_path))
img_paths.append(Path("/home/virtuag/www/storage/images_article") / (feature_path.stem + ".jpg"))
features = np.array(features)
query = fe.extract(img)
dists = np.linalg.norm(features-query, axis=1)
ids = np.argsort(dists)[:30]
scores = [img_paths[id] for id in ids]