Keras-yolo3 (FileNotFoundError: [Errno 2] No such file or directory: 'c:/test/images1\\hardhatvest') 에러

keras-yolo3로 학습을 하려고 했는데 도저히 에러 발생에서 해결을 못하겠습니다....

 주피터 노트북에서 실행했습니다

"""

Retrain the YOLO model for your own dataset.

"""

import os

from pathlib import Path

HOME_DIR = 'C:/test/'

ANNO_DIR = 'C:/test/label_xml/'

#xml 파일들

IMAGE_DIR = 'c:/test/images1/'

#이미지 파일들

print(ANNO_DIR)

print(IMAGE_DIR)

files = os.listdir(ANNO_DIR)

files2 = os.listdir(IMAGE_DIR)

print('파일 개수는:',len(files))

print('파일 개수는:',len(files2))

import numpy as np

import tensorflow.keras.backend as K

from keras.layers import Input, Lambda

from keras.models import *

from keras.optimizers import Adam

from keras.callbacks import TensorBoard, ModelCheckpoint, ReduceLROnPlateau, EarlyStopping

from tensorflow.python.ops import control_flow_ops

import sys

LOCAL_PACKAGE_DIR = os.path.abspath("c:/test/SED")

sys.path.append(LOCAL_PACKAGE_DIR)

from yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss

from yolo3.utils import get_random_data

from train import get_classes, get_anchors

from train import create_model, data_generator, data_generator_wrapper

annotation_path = 'c:/test/label_xml/annotation.csv'

log_dir = 'c:/test/logs/000/'

classes_path = 'c:/test/model_data/voc_classes.txt'

anchors_path = 'c:/test/model_data/yolo_anchors.txt'

class_names = get_classes(classes_path)

num_classes = len(class_names)

anchors = get_anchors(anchors_path)

model_weights_path = 'c:/test/model_data/yolo.h5'

input_shape = (416,416)

is_tiny_version = len(anchors)==6 # default setting

# create_tiny_model(), create_model() 함수의 인자 설정을 원본 train.py에서 수정.

if is_tiny_version:

model = create_tiny_model(input_shape, anchors, num_classes,

freeze_body=2, weights_path=model_weights_path)

else:

# create_model 은 해당 패키지의 tarin.py 내부에 있는 클래스를 사용했다. 이 함수는 keras 모듈이 많이 사용한다. 우선 모르는 건 pass하고 넘어가자.

model = create_model(input_shape, anchors, num_classes,

freeze_body=2, weights_path=model_weights_path) # make sure you know what you freeze

# epoch 마다 call back 하여 모델 파일 저장.

# 이것 또한 Keras에서 많이 사용하는 checkpoint 저장 방식인듯 하다. 우선 이것도 모르지만 넘어가자.

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 # train data : val_data = 9 : 1

with open(annotation_path) as f:

# 이러니 annotation 파일이 txt이든 csv이든 상관없었다.

lines = f.readlines()

# 랜덤 시드 생성 및 lines 셔플하기

np.random.seed(10101)

np.random.shuffle(lines)

np.random.seed(None)

# 데이터셋 나누기

num_val = int(len(lines)*val_split)

num_train = len(lines) - num_val

# 여기서 부터 진짜 학습 시작!

# create_model() 로 반환된 yolo모델에서 trainable=False로 되어 있는 layer들 제외하고 학습

if True:

# optimizer와 loss 함수 정의

# 위에서 사용한 create_model 클래스의 맴버함수를 사용한다.

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 = 4

print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))

# foward -> backpropagation -> weight 갱신 -> weight 저장

# checkpoint 만드는 것은 뭔지 모르겠으니 pass...

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')

# create_model() 로 반환된 yolo모델에서 trainable=False로 되어 있는 layer들 없이, 모두 True로 만들고 다시 학습

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')

이렇게 해주고 실행을 했습니다. 이미지 경로도 제대로 설정해줬는데 파일이나 폴더를 찾을 수가 없다고 하는데 어떻게 해주어야 할까요....

저 images1 폴더를 다른 이름으로 수정하거나 없애도 경로가 계속 'c:/test/images1\\hardhatvest' 이곳을 가리킵니다.

Train on 29 samples, val on 3 samples, with batch size 4.
Epoch 1/50

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_20040\2424985784.py in <module>
     20             epochs=50,
     21             initial_epoch=0,
---> 22             callbacks=[logging, checkpoint])
     23     model.save_weights(log_dir + 'trained_weights_stage_1.h5')
     24 

~\anaconda3\envs\test\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
     89                 warnings.warn('Update your `' + object_name + '` call to the ' +
     90                               'Keras 2 API: ' + signature, stacklevel=2)
---> 91             return func(*args, **kwargs)
     92         wrapper._original_function = func
     93         return wrapper

~\anaconda3\envs\test\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
   1730             use_multiprocessing=use_multiprocessing,
   1731             shuffle=shuffle,
-> 1732             initial_epoch=initial_epoch)
   1733 
   1734     @interfaces.legacy_generator_methods_support

~\anaconda3\envs\test\lib\site-packages\keras\engine\training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
    183             batch_index = 0
    184             while steps_done < steps_per_epoch:
--> 185                 generator_output = next(output_generator)
    186 
    187                 if not hasattr(generator_output, '__len__'):

~\anaconda3\envs\test\lib\site-packages\keras\utils\data_utils.py in get(self)
    740                     "`use_multiprocessing=False, workers > 1`."
    741                     "For more information see issue #1638.")
--> 742             six.reraise(*sys.exc_info())

~\anaconda3\envs\test\lib\site-packages\six.py in reraise(tp, value, tb)
    717             if value.__traceback__ is not tb:
    718                 raise value.with_traceback(tb)
--> 719             raise value
    720         finally:
    721             value = None

~\anaconda3\envs\test\lib\site-packages\keras\utils\data_utils.py in get(self)
    709                 try:
    710                     future = self.queue.get(block=True)
--> 711                     inputs = future.get(timeout=30)
    712                     self.queue.task_done()
    713                 except mp.TimeoutError:

~\anaconda3\envs\test\lib\multiprocessing\pool.py in get(self, timeout)
    655             return self._value
    656         else:
--> 657             raise self._value
    658 
    659     def _set(self, i, obj):

~\anaconda3\envs\test\lib\multiprocessing\pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
    119         job, i, func, args, kwds = task
    120         try:
--> 121             result = (True, func(*args, **kwds))
    122         except Exception as e:
    123             if wrap_exception and func is not _helper_reraises_exception:

~\anaconda3\envs\test\lib\site-packages\keras\utils\data_utils.py in next_sample(uid)
    648         The next value of generator `uid`.
    649     """
--> 650     return six.next(_SHARED_SEQUENCES[uid])
    651 
    652 

c:\test\train.py in data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes)
    177             if i==0:
    178                 np.random.shuffle(annotation_lines)
--> 179             image, box = get_random_data(annotation_lines[i], input_shape, random=True)
    180             image_data.append(image)
    181             box_data.append(box)

c:\test\yolo3\utils.py in get_random_data(annotation_line, input_shape, random, max_boxes, jitter, hue, sat, val, proc_img)
     37     '''random preprocessing for real-time data augmentation'''
     38     line = annotation_line.split()
---> 39     image = Image.open(line[0])
     40     iw, ih = image.size
     41     h, w = input_shape

~\anaconda3\envs\test\lib\site-packages\PIL\Image.py in open(fp, mode, formats)
   3090 
   3091     if filename:
-> 3092         fp = builtins.open(filename, "rb")
   3093         exclusive_fp = True
   3094 

FileNotFoundError: [Errno 2] No such file or directory: 'c:/test/images1\\hardhatvest'