我们从Python开源项目中，提取了以下6个代码示例，用于说明如何使用model.load_model()。
def test_file(): count = 1 face_cascade = cv2.CascadeClassifier( '/usr/local/opt/opencv3/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml') argvs = sys.argv for argv in argvs[1:]: img = cv2.imread(argv) if type(img) != str: try: gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) print('convert succeed') except: print('can not convert to gray image') continue faces = face_cascade.detectMultiScale(gray, 1.3, 5) for (x, y, w, h) in faces: f = cv2.resize(gray[y:(y + h), x:(x + w)], (128, 128)) model = load_model('/Users/songheqi/model/model.h5') num, acc = predict(model, f, 128) name_list = read_name_list('/Users/songheqi/train_set/') print('The {} picture is '.format(count) + name_list[num] + ' acc : ', acc) count += 1
def main(): model = load_model(args.model_dir) assert model is not None vocab, vocab_inv = load_vocab(args.model_dir) assert vocab is not None assert vocab_inv is not None vocab_size = model.vocab_size with chainer.using_config("train", False): for n in range(args.num_generate): word_ids = np.arange(0, vocab_size, dtype=np.int32) token = ID_BOS x = np.asarray([[token]]).astype(np.int32) model.reset_state() while token != ID_EOS and x.shape[1] < args.max_sentence_length: u = model.forward_one_step(x) p = F.softmax(u).data[-1] token = np.random.choice(word_ids, size=1, p=p) x = np.append(x, np.asarray([token]).astype(np.int32), axis=1) sentence = [] for token in x[0]: word = vocab_inv[token] sentence.append(word) print(" ".join(sentence))
def main(args): model = load_model(args.model_dir) assert model is not None vocab, vocab_inv = load_vocab(args.model_dir) assert vocab is not None assert vocab_inv is not None vocab_size = model.vocab_size with chainer.using_config("train", False): for n in xrange(args.num_generate): word_ids = np.arange(0, vocab_size, dtype=np.int32) token = ID_BOS x = np.asarray([[token]]).astype(np.int32) model.reset_state() while token != ID_EOS and x.shape[1] < args.max_sentence_length: u = model.forward_one_step(x) p = F.softmax(u).data[-1] token = np.random.choice(word_ids, size=1, p=p) x = np.append(x, np.asarray([token]).astype(np.int32), axis=1) sentence = [] for token in x[0]: word = vocab_inv[token] sentence.append(word) print(" ".join(sentence))
def test_camera(): face_patterns = cv2.CascadeClassifier( '/usr/local/opt/opencv3/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml') cameraCapture = cv2.VideoCapture(0) success, frame = cameraCapture.read() while True: success, frame = cameraCapture.read() gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) # ???? faces = face_patterns.detectMultiScale(gray, 1.3, 5) # ???? for (x, y, w, h) in faces: frame = cv2.rectangle( frame, (x, y), (x + w, y + h), (255, 0, 0), 2) # ????????????? f = cv2.resize(gray[y:(y + h), x:(x + w)], (128, 128)) model = load_model('/Users/songheqi/model/model.h5') num, acc = predict(model, f, 128) name_list = read_name_list('/Users/songheqi/train_set/') print('You are ' + name_list[num] + ' acc : ', acc) cv2.imshow("Camera", frame) if cv2.waitKey(1) & 0xFF == ord('q'): # ?‘q’??? break cameraCapture.release() cv2.destroyAllWindows()
def main(): # ???????? vocab, vocab_inv, BLANK = get_vocab() vocab_size = len(vocab) # ??????????????? # GTX 1080 1??? batchsizes = [96, 64, 64, 64, 64, 64, 64, 64, 48, 48, 48, 32, 32, 24, 24, 24, 24, 24, 24, 24, 24, 24] augmentation = AugmentationOption() if args.augmentation: augmentation.change_vocal_tract = True augmentation.change_speech_rate = True augmentation.add_noise = True model = load_model(args.model_dir) assert model is not None if args.gpu_device >= 0: chainer.cuda.get_device(args.gpu_device).use() model.to_gpu(args.gpu_device) xp = model.xp # ??? with chainer.using_config("train", False): iterator = TestMinibatchIterator(wav_path_test, trn_path_test, cache_path, batchsizes, BLANK, buckets_limit=args.buckets_limit, option=augmentation, gpu=args.gpu_device >= 0) buckets_errors = [] for batch in iterator: x_batch, x_length_batch, t_batch, t_length_batch, bucket_idx, progress = batch if args.filter_bucket_id and bucket_idx != args.filter_bucket_id: continue sys.stdout.write("\r" + stdout.CLEAR) sys.stdout.write("computing CER of bucket {} ({} %)".format(bucket_idx + 1, int(progress * 100))) sys.stdout.flush() y_batch = model(x_batch, split_into_variables=False) y_batch = xp.argmax(y_batch.data, axis=2) error = compute_minibatch_error(y_batch, t_batch, BLANK, print_sequences=True, vocab=vocab_inv) while bucket_idx >= len(buckets_errors): buckets_errors.append([]) buckets_errors[bucket_idx].append(error) avg_errors = [] for errors in buckets_errors: avg_errors.append(sum(errors) / len(errors)) sys.stdout.write("\r" + stdout.CLEAR) sys.stdout.flush() print_bold("bucket CER") for bucket_idx, error in enumerate(avg_errors): print("{} {}".format(bucket_idx + 1, error * 100))
def main(args): vocab, vocab_inv = load_vocab(args.model_dir) vocab_source, vocab_target = vocab vocab_inv_source, vocab_inv_target = vocab_inv source_dataset, target_dataset = read_data(vocab_source, vocab_target, args.source_train, None, args.source_dev, None, args.source_test, None, reverse_source=True) source_dataset_train, source_dataset_dev, source_dataset_test = source_dataset target_dataset_train, target_dataset_dev, target_dataset_test = target_dataset printb("data #") if len(source_dataset_train) > 0: print("train {}".format(len(source_dataset_train))) if len(source_dataset_dev) > 0: print("dev {}".format(len(source_dataset_dev))) if len(source_dataset_test) > 0: print("test {}".format(len(source_dataset_test))) # split into buckets source_buckets_train = None if len(source_dataset_train) > 0: printb("buckets #data (train)") source_buckets_train = make_buckets(source_dataset_train) if args.buckets_slice is not None: source_buckets_train = source_buckets_train[:args.buckets_slice + 1] for size, data in zip(bucket_sizes, source_buckets_train): print("{} {}".format(size, len(data))) source_buckets_dev = None if len(source_dataset_dev) > 0: printb("buckets #data (dev)") source_buckets_dev = make_buckets(source_dataset_dev) if args.buckets_slice is not None: source_buckets_dev = source_buckets_dev[:args.buckets_slice + 1] for size, data in zip(bucket_sizes, source_buckets_dev): print("{} {}".format(size, len(data))) source_buckets_test = None if len(source_dataset_test) > 0: printb("buckets #data (test)") source_buckets_test = make_buckets(source_dataset_test) if args.buckets_slice is not None: source_buckets_test = source_buckets_test[:args.buckets_slice + 1] for size, data in zip(bucket_sizes, source_buckets_test): print("{} {}".format(size, len(data))) # init model = load_model(args.model_dir) assert model is not None if args.gpu_device >= 0: cuda.get_device(args.gpu_device).use() model.to_gpu() if source_buckets_train is not None: dump_source_translation(model, source_buckets_train, vocab_inv_source, vocab_inv_target, beam_width=args.beam_width, normalization_alpha=args.alpha) if source_buckets_dev is not None: dump_source_translation(model, source_buckets_dev, vocab_inv_source, vocab_inv_target, beam_width=args.beam_width, normalization_alpha=args.alpha) if source_buckets_test is not None: dump_source_translation(model, source_buckets_test, vocab_inv_source, vocab_inv_target, beam_width=args.beam_width, normalization_alpha=args.alpha)
