FileNotFoundError：[错误2]没有这样的文件或目录：'./ckpt/yolov2-12.profile'

Question

我正在使用Darkflow在自定义数据集上进行对象检测。虽然所有迭代后的训练模型都没有保存到ckpt文件夹，但在darkflow中没有这样的文件夹。所以我创建了一个，但仍然抛出一个错误：

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np


import cv2

from darkflow.net.build import TFNet

history = {"model": "C:/Users/Jayachander/Desktop/Desktop/Object-Detection/Dataset/yolov2.cfg",
           "load": "C:/Users/Jayachander/Desktop/Desktop/Object-Detection/Dataset/yolov2.weights",
           "batch": 8,
           "epoch": 2,
           "gpu": 1.0,
           "train": True,
           "annotation": "C:/Users/Jayachander/Desktop/Desktop/Object-Detection/Dataset/Stumps/voc",
           "dataset": "C:/Users/Jayachander/Desktop/Desktop/Object-Detection/Dataset/Stumps/images"}

tfnet = TFNet(history)


tfnet.train()

C:/Users/Jayachander/Desktop/Desktop/Object-Detection/Dataset/yolov2.cfg parsing C:/Users/Jayachander/Desktop/Desktop/Object-Detection/Dataset/Stumps/voc

Parsing for ['Ball', 'Bat', 'Batsman', 'Stumps', 'Stumpsdown', 'keeper', 'person', 'Player'] 

[====================>]100%  VRP9621.xml2.xml

Statistics:

keeper: 13

person: 5

Dataset size: 50

Dataset of 50 instance(s)

Training statistics: 

    Learning rate : 1e-05

    Batch size    : 8

    Epoch number  : 2

    Backup every  : 2000

step 1 - loss 226.4876251220703 - moving ave loss 226.48762512207034

step 2 - loss 226.22042846679688 - moving ave loss 226.460905456543

step 3 - loss 226.63307189941406 - moving ave loss 226.47812210083012

step 4 - loss 226.4044647216797 - moving ave loss 226.4707563629151

step 5 - loss 226.2371826171875 - moving ave loss 226.44739898834234

step 6 - loss 226.49505615234375 - moving ave loss 226.4521647047425

Finish 1 epoch(es)

step 7 - loss 226.44583129882812 - moving ave loss 226.45153136415107

step 8 - loss 226.27183532714844 - moving ave loss 226.4335617604508

step 9 - loss 226.13697814941406 - moving ave loss 226.40390339934714

step 10 - loss 226.24066162109375 - moving ave loss 226.38757922152183

step 11 - loss 226.10202026367188 - moving ave loss 226.35902332573687

step 12 - loss 226.3309326171875 - moving ave loss 226.35621425488193

Finish 2 epoch(es)

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
<ipython-input-5-b9fb94a28d0a> in <module>
----> 1 tfnet.train()


~\Anaconda3\lib\site-packages\darkflow\net\flow.py in train(self)

     72         if not ckpt: _save_ckpt(self, *args)

     73 

---> 74     if ckpt: _save_ckpt(self, *args)

     75 

     76 def return_predict(self, im):


~\Anaconda3\lib\site-packages\darkflow\net\flow.py in _save_ckpt(self, step, loss_profile)

     21     profile = file.format(model, step, '.profile')

     22     profile = os.path.join(self.FLAGS.backup, profile)

---> 23     with open(profile, 'wb') as profile_ckpt:

     24         pickle.dump(loss_profile, profile_ckpt)

     25 


FileNotFoundError: [Errno 2] No such file or directory: './ckpt/yolov2-12.profile'