jhasuman / potholes-detection Goto Github PK

See error above.

In fact, looking in the config file, there is no "backend' parameter in model object:

How to resolve?

File "predict.py", line 46, in main
yolo = YOLO(backend = config['model']['backend'],
KeyError: 'backend'

What backend should be used for this pretrained model.?
Please help as soon as possible.

Please attach the updated weight link as soon as possible

I want to request for information such as accuracy or confusion matrix of the model

Traceback (most recent call last):
File "train.py", line 101, in
main(args)
File "train.py", line 34, in main
config['model']['labels'])
File "/home/yash/Desktop/potholes-detection-master/preprocessing.py", line 19, in parse_annotation
tree = ET.parse(ann_dir + ann)
File "/home/yash/anaconda3/envs/PythonGPU/lib/python3.6/xml/etree/ElementTree.py", line 1196, in parse
tree.parse(source, parser)
File "/home/yash/anaconda3/envs/PythonGPU/lib/python3.6/xml/etree/ElementTree.py", line 597, in parse
self._root = parser._parse_whole(source)
xml.etree.ElementTree.ParseError: not well-formed (invalid token): line 1, column 0

facing error
unable to open trained_wts.h5
please help asap.

get this error whenever i execute predict.py

I run this command line

python predict.py -c config.json -w weights/trained_wts.h5 -i images/1.jpg

and get error
ValueError: You are trying to load a weight file containing 2 layers into a model with 44 layers.

any ideas how to fix it

Thank you

link provided for weight dosent work

Traceback (most recent call last):
File "predict.py", line 96, in
main(args)
File "predict.py", line 56, in main
yolo.load_weights(weights_path)
File "D:\potholes-detection-master\potholes-detection-master\frontend.py", line 243, in load_weights
self.model.load_weights(weight_path)
File "I:\Anaconda\lib\site-packages\keras\engine\network.py", line 1157, in load_weights
with h5py.File(filepath, mode='r') as f:
File "I:\Anaconda\lib\site-packages\h5py_hl\files.py", line 408, in init
swmr=swmr)
File "I:\Anaconda\lib\site-packages\h5py_hl\files.py", line 173, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py\h5f.pyx", line 88, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = '/path/to/trained_wts.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

Can someone help me with training 'train.py' with my own data set just to improve the accuracy?
And also it'll be very helpful if someone can explain what exactly is happening when 'predict.py' runs.
Thanks a lot!

cant figure out the model's name and how to save this model in .pb file ?

Can i please get the dataset used for training this model

Can anyone help please?

Traceback (most recent call last):
File "predict.py", line 96, in
main(args)
File "predict.py", line 56, in main
yolo.load_weights(weights_path)
File "D:\potholes-detection-master\potholes-detection-master\frontend.py", line 243, in load_weights
self.model.load_weights(weight_path)
File "I:\Anaconda\lib\site-packages\keras\engine\network.py", line 1157, in load_weights
with h5py.File(filepath, mode='r') as f:
File "I:\Anaconda\lib\site-packages\h5py_hl\files.py", line 408, in init
swmr=swmr)
File "I:\Anaconda\lib\site-packages\h5py_hl\files.py", line 173, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py\h5f.pyx", line 88, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = '/path/to/full_yolo_backend.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)