ankitAMD
commented
4 years ago Currently I have two files in build/graph folder: tiny-yolo-voc-52c.meta tiny-yolo-voc-52c.pb
I'm trying to run the following script
import cv2 #Open Source Computer Vision is a library which helps in real-time computer vision and used for Image Processing from darkflow.net.build import TFNet #Tfnet is a class in build.py python files through which Translate darknet to tensorflow. import matplotlib.pyplot as plt #it is used for data visualization #%config InlineBackend.figure_format = 'svg' # define the model options and run # Training the model # define the model options and run #This step involves training your model based on dataset and labels you generated* options = { 'metaLoad':"built_graph/tiny-yolo-voc-52c.meta", 'pbLoad':"built_graph/tiny-yolo-voc-52c.pb", 'threshold': 0.07, 'cpu': 1.0 } tfnet = TFNet(options)I don't understand the error What can I do to fix it?
C:\Users\Mikko\PycharmProjects\Darknet_project\venv\Scripts\python.exe C:/Users/Mikko/PycharmProjects/Darknet_project/Main.py C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) Loading from .pb and .meta WARNING:tensorflow:From C:\Users\Mikko\PycharmProjects\Darknet_project\darkflow-master\darkflow\net\build.py:82: FastGFile.__init__ (from tensorflow.python.platform.gfile) is deprecated and will be removed in a future version. Instructions for updating: Use tf.gfile.GFile. Traceback (most recent call last): File "C:/Users/Mikko/PycharmProjects/Darknet_project/Main.py", line 22, in <module> tfnet = TFNet(options) File "C:\Users\Mikko\PycharmProjects\Darknet_project\darkflow-master\darkflow\net\build.py", line 55, in __init__ self.build_from_pb() File "C:\Users\Mikko\PycharmProjects\Darknet_project\darkflow-master\darkflow\net\build.py", line 84, in build_from_pb graph_def.ParseFromString(f.read()) File "C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 125, in read self._preread_check() File "C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 85, in _preread_check compat.as_bytes(self.__name), 1024 * 512, status) File "C:\Users\Mikko\PycharmProjects\Darknet_project\venv\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in __exit__ c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: built_graph/tiny-yolo-voc-52c.pb : The system cannot find the path specified. ; No such process Process finished with exit code 1
First thing i have suggested if you running code using my github then i have some condition. My condition is i have not enough memory to run the code so i use very small layers of neural network (tiny-yolo.cfg) . I have not have GPU so that's why i am not using GPU. I have very very less training dataset for training. I am not using Pycharm. I am using Jupyter Notebook. I am using Tensorflow. I am using Ubuntu 16.04 as OS. I am using threshold very less 0.07 which are very poor (7/100) this is because not enough dataset and training processor,memory. So i have only want to try to check myself that is i can run this project or not . If you using enough dataset and GPU processing power than increase the threshold . change the thresold at last time to check results and output.
Currently I have two files in build/graph folder: tiny-yolo-voc-52c.meta tiny-yolo-voc-52c.pb
I'm trying to run the following script
I don't understand the error What can I do to fix it?