Error in loading the saved optimizer state. As a result, your model is starting with a freshly initialized optimizer.
warnings.warn('Error in loading the saved optimizer '

hey i also tried to run train_detection.py i am facing this error while train the PKLot dataset.
here is the error:-
Traceback (most recent call last):
File "train_detection.py", line 95, in
validX[counter_test] = img
IndexError: index 216649 is out of bounds for axis 0 with size 216649

I was trying to execute your test_images.py script with PKLot dataset , but i was getting an error.
Here is the error....
/home/rashmi/.virtualenvs/dl4cv/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as register_converters
Using TensorFlow backend.
/home/rashmi/.virtualenvs/dl4cv/lib/python3.6/importlib/bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
return f(*args, **kwds)
2018-03-28 16:27:40.455187: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-03-28 16:27:40.678485: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-03-28 16:27:40.678921: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1050 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.506
pciBusID: 0000:01:00.0
totalMemory: 3.94GiB freeMemory: 2.08GiB
2018-03-28 16:27:40.678938: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1050 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)
/home/rashmi/.virtualenvs/dl4cv/lib/python3.6/site-packages/keras/models.py:291: UserWarning: Error in loading the saved optimizer state. As a result, your model is starting with a freshly initialized optimizer.
warnings.warn('Error in loading the saved optimizer '
8/8 [==============================] - 35s 4s/step
[ INFO:0] Initialize OpenCL runtime...
Traceback (most recent call last):
File "test_images.py", line 69, in
im = cv2.rectangle(im,(y,x+2),(y+y_shift,x+x_shift-2),(255*(predictions[i]),255*(1-predictions[i]),0),2)
TypeError: Scalar value for argument 'color' is not numeric

Hey, first of all great project! I tried to recreate your parking_lot_detection python scripts, but got some problems in train_detection.
I downloaded the following database here PKLot.tar.gz but it seems to have a different structure compared to your database.

Could you give me an example, what your directory looked like or maybe even upload it somewhere to share it? I could offer you some temporary cloud storage.

Thanks in advance!