def predict():
''' Predict the class of an image.
We need to run it through the same pipeline as before (run the image through the pre-trained VGG16 model and then run the bottleneck prediction through the trained top model).
'''
# load the class_indices saved in the earlier step
class_dictionary = np.load('cache/class_indices.npy',
allow_pickle=True).item()
num_classes = len(class_dictionary)
# add the path to your test image below
dbTest = Database(DB_dir="CorelDBDataSet/test",
DB_csv="CorelDBDataSetTest.csv")
print("[INFO] loading and preprocessing image...")
for image_path in dbTest.get_data().img:
image = load_img(image_path, target_size=(img_width, img_height))
image = img_to_array(image)
# important! otherwise the predictions will be '0'
image = image / 255
image = np.expand_dims(image, axis=0)
# build the VGG16 network
model = applications.VGG16(include_top=False, weights='imagenet')
# get the bottleneck prediction from the pre-trained VGG16 model
bottleneck_prediction = model.predict(image)
# build top model
model = Sequential()
model.add(Flatten(input_shape=bottleneck_prediction.shape[1:]))
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='sigmoid'))
model.load_weights(top_model_weights_path)
# use the bottleneck prediction on the top model to get the final classification
class_predicted = model.predict_classes(bottleneck_prediction)
inID = class_predicted[0]
inv_map = {v: k for k, v in class_dictionary.items()}
label = inv_map[inID]
probabilities = model.predict_proba(bottleneck_prediction)[0][inID]
# get the predicted label
print("Image: {}, Predicted label: {}, Probability: {}".format(
image_path, label, probabilities))
value = item['index']
link = item['link']
querry = '''UPDATE products set {}={} WHERE LINK='{}' '''.format(
tmp.upper(), value, link)
cur.execute(querry)
self.con.commit()
self.con.close()
except:
return False
def close(self):
self.con.close()
return True
if __name__ == '__main__':
db = Database()
data = db.get_data()
sql = SQLite()
sql.insertmuti(db)
sql.update('10000.jpg', 'res', 1)
tmp = sql.select('res', 1)
for d in data.itertuples():
d_img, d_cls, d_file = getattr(d, "img"), getattr(d, "cls"), getattr(
d, "filename")
sql.insert(d_cls, d_file, d_img)
sql.close()
d_hist = self.histogram(d_img, type=h_type, n_slice=n_slice)
samples.append({'img': d_img, 'cls': d_cls, 'hist': d_hist})
cPickle.dump(
samples, open(os.path.join(cache_dir, sample_cache), "wb",
True))
return samples
if __name__ == "__main__":
#On met en place les deux bases
DB_train_dir_param = "../../ReseauDeNeurones/data/train"
DB_train_csv_param = "database/data_train.csv"
db_train = Database(DB_train_dir_param, DB_train_csv_param)
data_train = db_train.get_data()
DB_test_dir_param = "../../ReseauDeNeurones/data/test"
DB_test_csv_param = "database/data_test.csv"
db_test = Database(DB_test_dir_param, DB_test_csv_param)
data_test = db_test.get_data()
edge = Edge()
# check shape
assert edge_kernels.shape == (5, 2, 2)
# evaluate database
APs, prevision = my_evaluate_class(db_train,
db_test,
f_class=Edge,
d_type=d_type,