YOLO v3での機械学習中のエラー ResourceExhaustedError

Question

前提・実現したいこと

yolov3を使用し，自作のデータセットを作成しようと試みています．データを学習させている際，以下のようなエラーコードが現れ，学習がストップします．また毎回学習がepoch50/100で終了しています．

発生している問題・エラーメッセージ

tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[1,1,512,256] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node training_1/Adam/gradients/conv2d_32/Square_grad/Mul_1 (defined at C:\Users\KIT_EA_FC_PC017\Anaconda3\envs\keras-deeplearning\lib\site-packages\keras\backend\tensorflow_backend.py:2515) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

         [[node loss_1/add_74 (defined at C:\Users\KIT_EA_FC_PC017\Anaconda3\envs\keras-deeplearning\lib\site-packages\keras\engine\training.py:848) ]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

該当のソースコード

"""
Retrain the YOLO model for your own dataset.
"""

import numpy as np
import keras.backend as K
from keras.layers import Input, Lambda
from keras.models import Model
from keras.optimizers import Adam
from keras.callbacks import TensorBoard, ModelCheckpoint, ReduceLROnPlateau, EarlyStopping

from yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss
from yolo3.utils import get_random_data
import sys

def _main():
    annotation_path = 'model_data/2007_train.txt'
    log_dir = 'G:/logs'
    classes_path = 'model_data/voc_classes.txt'
    anchors_path = 'model_data/yolo_anchors.txt'
    class_names = get_classes(classes_path)
    num_classes = len(class_names)
    anchors = get_anchors(anchors_path)

    input_shape = (320,320) # multiple of 32, hw
    if len(sys.argv) > 1:
        input_shape = (int(sys.argv[1]),int(sys.argv[1]))

    is_tiny_version = len(anchors)==6 # default setting
    if is_tiny_version:
        model = create_tiny_model(input_shape, anchors, num_classes,
            freeze_body=2, weights_path='model_data/tiny_yolo_weights.h5')
    else:
        model = create_model(input_shape, anchors, num_classes,
            freeze_body=2, weights_path='model_data/yolo_weights.h5') # make sure you know what you freeze

    logging = TensorBoard(log_dir=log_dir)
    checkpoint = ModelCheckpoint(log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
        monitor='val_loss', save_weights_only=True, save_best_only=True, period=3)
    reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3, verbose=1)
    early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1)

    val_split = 0.1
    with open(annotation_path) as f:
        lines = f.readlines()
    np.random.seed(10101)
    np.random.shuffle(lines)
    np.random.seed(None)
    num_val = int(len(lines)*val_split)
    num_train = len(lines) - num_val

    # Train with frozen layers first, to get a stable loss.
    # Adjust num epochs to your dataset. This step is enough to obtain a not bad model.
    if True:
        model.compile(optimizer=Adam(lr=1e-3), loss={
            # use custom yolo_loss Lambda layer.
            'yolo_loss': lambda y_true, y_pred: y_pred})

        batch_size = 8
        if len(sys.argv) > 2:
            batch_size = int(sys.argv[2])

        print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
        model.fit_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, anchors, num_classes),
                steps_per_epoch=max(1, num_train//batch_size),
                validation_data=data_generator_wrapper(lines[num_train:], batch_size, input_shape, anchors, num_classes),
                validation_steps=max(1, num_val//batch_size),
                epochs=50,
                initial_epoch=0,
                callbacks=[logging, checkpoint])
        model.save_weights(log_dir + 'trained_weights_stage_1.h5')

    # Unfreeze and continue training, to fine-tune.
    # Train longer if the result is not good.
    if True:
        for i in range(len(model.layers)):
            model.layers[i].trainable = True
        model.compile(optimizer=Adam(lr=1e-4), loss={'yolo_loss': lambda y_true, y_pred: y_pred}) # recompile to apply the change
        print('Unfreeze all of the layers.')

        batch_size = 4 # note that more GPU memory is required after unfreezing the body
        print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
        model.fit_generator(data_generator_wrapper(lines[:num_train], batch_size, input_shape, anchors, num_classes),
            steps_per_epoch=max(1, num_train//batch_size),
            validation_data=data_generator_wrapper(lines[num_train:], batch_size, input_shape, anchors, num_classes),
            validation_steps=max(1, num_val//batch_size),
            epochs=100,
            initial_epoch=50,
            callbacks=[logging, checkpoint, reduce_lr, early_stopping])
        model.save_weights(log_dir + 'trained_weights_final.h5')

    # Further training if needed.


def get_classes(classes_path):
    '''loads the classes'''
    with open(classes_path) as f:
        class_names = f.readlines()
    class_names = [c.strip() for c in class_names]
    return class_names

def get_anchors(anchors_path):
    '''loads the anchors from a file'''
    with open(anchors_path) as f:
        anchors = f.readline()
    anchors = [float(x) for x in anchors.split(',')]
    return np.array(anchors).reshape(-1, 2)


def create_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
            weights_path='model_data/yolo_weights.h5'):
    '''create the training model'''
    K.clear_session() # get a new session
    image_input = Input(shape=(None, None, 3))
    h, w = input_shape
    num_anchors = len(anchors)

    y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \
        num_anchors//3, num_classes+5)) for l in range(3)]

    model_body = yolo_body(image_input, num_anchors//3, num_classes)
    print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))

    if load_pretrained:
        model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
        print('Load weights {}.'.format(weights_path))
        if freeze_body in [1, 2]:
            # Freeze darknet53 body or freeze all but 3 output layers.
            num = (185, len(model_body.layers)-3)[freeze_body-1]
            for i in range(num): model_body.layers[i].trainable = False
            print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))

    model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
        arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
        [*model_body.output, *y_true])
    model = Model([model_body.input, *y_true], model_loss)

    return model

def create_tiny_model(input_shape, anchors, num_classes, load_pretrained=True, freeze_body=2,
            weights_path='model_data/tiny_yolo_weights.h5'):
    '''create the training model, for Tiny YOLOv3'''
    K.clear_session() # get a new session
    image_input = Input(shape=(None, None, 3))
    h, w = input_shape
    num_anchors = len(anchors)

    y_true = [Input(shape=(h//{0:32, 1:16}[l], w//{0:32, 1:16}[l], \
        num_anchors//2, num_classes+5)) for l in range(2)]

    model_body = tiny_yolo_body(image_input, num_anchors//2, num_classes)
    print('Create Tiny YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))

    if load_pretrained:
        model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
        print('Load weights {}.'.format(weights_path))
        if freeze_body in [1, 2]:
            # Freeze the darknet body or freeze all but 2 output layers.
            num = (20, len(model_body.layers)-2)[freeze_body-1]
            for i in range(num): model_body.layers[i].trainable = False
            print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))

    model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
        arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.7})(
        [*model_body.output, *y_true])
    model = Model([model_body.input, *y_true], model_loss)

    return model

def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):
    '''data generator for fit_generator'''
    n = len(annotation_lines)
    i = 0
    while True:
        image_data = []
        box_data = []
        for b in range(batch_size):
            if i==0:
                np.random.shuffle(annotation_lines)
            image, box = get_random_data(annotation_lines[i], input_shape, random=True)
            image_data.append(image)
            box_data.append(box)
            i = (i+1) % n
        image_data = np.array(image_data)
        box_data = np.array(box_data)
        y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
        yield [image_data, *y_true], np.zeros(batch_size)

def data_generator_wrapper(annotation_lines, batch_size, input_shape, anchors, num_classes):
    n = len(annotation_lines)
    if n==0 or batch_size<=0: return None
    return data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes)

if __name__ == '__main__':
    _main()

試したこと

バッチ数を変更し，何度か試しています．恐らく上記のエラーはメモリ容量不足で生じていると考えています．ただ，このメモリ容量不足はwindowsCのメモリ不足なのかGPUのメモリ不足なのかが分かりません．
その部分も踏まえ教えて頂けると助かります．

補足情報（FW/ツールのバージョンなど）

GPU:NVIDIA GeForce GTX 960
GPUグラフィック容量(VRRAM):2007MB

Answer 1

GPUのメモリ不足です。
YOLOv3をGPUで動かすには最低8Gないと厳しいと思います。
パソコン向けのGPUの場合、RTX2070,RTX2080あたりです。

Comments

[ponzuuuuu]

コメントありがとうございます．
つまり，GPUグラフィック容量が足りないという事で間違いないでしょうか．
また，その容量を増やす方法などがあれば教えて頂けると助かります．

[tiitoi]

> GPUグラフィック容量が足りないという事で間違いないでしょうか．
はい

> その容量を増やす方法などがあれば教えて頂けると助かります

RAMメモリのようにメモリだけ増設するといったことはできないので、メモリが8G以上ある新しい Nvidia の GPU を購入して、差し替える必要があります。(ノートパソコンや一体型のようなパソコンだとそもそもグラボを変えたりするのは無理かもしれません。)

それか速度は落ちますが、CPU で動かす手もあります。