Traffic-Sign-Classifier | This project is made for Self Driving Car | Machine Learning library

I am following this tutorial to build a simple deep learning app for traffic sign recognition. link

I made an own model, and I also tried it with the model in this repository: link

When I run the app from xcode on my iPhone, I can see the picture of the camera, but the text always says "Label", no matter what is on the screen. The only thing I modified from the tutorial is that I hardcoded the classes before converting to mlmodel:

I am doing the self driving course with Udacity. There is a common environment which I launched in windows 10 and I was able to run tensorflow fine but I want to use the GPU.

My GPU is listed as compatible (GTX 950M).

I followed the tensorflow instructions on windows 10 to add the GPU:

https://www.tensorflow.org/install/install_windows

and downloaded and installed cuda_8.0.61_win10

Next I restarted my environment. I checked to see it was working with the simple python program:

I'm working on a neural net problem, and in the conv2d function, i'm getting a Type mismatch issue.

Here's the code snippet conv_layer1 = tf.nn.conv2d(inputs, w_layer1, strides=strides, padding='VALID') + b_layer1

I'm getting this error

TypeError: Expected binary or unicode string, got >

I tried having [1,1,1,1] inline aswell as a variable, but no luck

The complete error trace is here(search for "In [46]:" https://github.com/mymachinelearnings/CarND-Traffic-Sign-Classifier-Project/blob/attempt1/Traffic_Sign_Classifier.ipynb