def __init__(self):
# define class labels
self.class_labels = ["diamonds", "hearts", "spades", "clubs"]
# define preprocessors
self.pp = [SimplePreprocessor(32, 32), ImageToArrayPreprocessor()]
# load model
self.model = load_model("{}/model/lenet_cards.hdf5".format(currentdir))
import cv2
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", required=True, help="path to trained model")
ap.add_argument("-d", "--dataset", required=True, help="path to input dataset")
args = vars(ap.parse_args())
class_labels = ["diamonds", "hearts", "spades", "three_sisters"]
print("[INFO] sampling images")
image_paths = np.array(list(paths.list_images(args["dataset"])))
idxs = np.random.randint(0, len(image_paths), size=(10, ))
image_paths = image_paths[idxs]
sp = SimplePreprocessor(32, 32)
iap = ImageToArrayPreprocessor()
sdl = SimpleDatasetLoader(preprocessors=[sp, iap])
(data, labels) = sdl.load(image_paths)
data = data.astype("float") / 255.0
print("[INFO] loading model...")
model = load_model(args["model"])
print("[INFO] predicting...")
preds = model.predict(data, batch_size=32).argmax(axis=1)
for (i, image_path) in enumerate(image_paths):
image = cv2.imread(image_path)
# cv2.putText(image, , (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2)
print("[INFO] Label: {}".format(class_labels[preds[i]]))
from preprocessing.ImageToArrayPreprocessor import ImageToArrayPreprocessor
from utils.ranked import rank5_acc
from io.hdf5DatasetReader import HDF5DatasetReader
from keras.models import load_model
import numpy as np
import progressbar
import json
# Load the RGB means for the training set.
means = json.loads(open(config.DATASET_MEAN).read())
# Initialize the image preprocessors.
sp = SimplePreprocessor(width=64, height=64)
cp = CropPreprocessor(width=64, height=64)
mp = MeanPreprocessor(rMean=means["R"], gMean=means["G"], bMean=means["B"])
iap = ImageToArrayPreprocessor()
# Loading the pre-trained model.
print("[INFO] loading model...")
model = load_model(config.MODEL_PATH)
# Initialize the testing dataset generator, then make predictions on the testing data.
# First obtain a baseline on the testing set using only the original testing images as input to the trained model.
print("[INFO] predicting on test data (no crops)...")
testGen = HDF5DatasetReader(config.TEST_HDF5, batchSize=config.BATCH_SIZE, preprocessors=[sp, mp, iap], classes=config.NUM_CLASSES)
# Predict on the test dataset.
print("[INFO] predicting on test data...")
predictions = model.predict_generator(testGen.generator(),
steps=testGen.numImages // config.BATCH_SIZE,
max_queue_size=config.BATCH_SIZE * 2)