image-classifier | triplet loss , batch triplet loss | Machine Learning library

I've retrained a Mobilenet V1 model using my own dataset. Right now, I'm trying to get my model to load into this example project: https://github.com/shivangidas/image-classifier

It keeps throwing the following error

I have been trying to run my Python API (using Flask) with Docker for a while, but keep running into this issue:

ModuleNotFoundError: No module named 'flask'

Running this on Mac OS X (10.14.5) with Docker version 19.03.1, build 74b1e89.

My Dockerfile looks like this:

I am following a tutorial on TensorFlow image classifications.

My use case differs slightly from the tutorial, it uses Chess pieces, whereas I am using traffic lights, and want to detect if its red, green or amber.

I am finding that the results of my tests are poor,and wonder if it is to do with the cv2.IMREAD_GRAYSCALE I see in the CreateData section of the tutorial. Of course colour matters in my classifier, so I wonder if the tutorial is converting to greyscale, hence my lack of accurate results.

I therefore changed all references of cv2.IMREAD_GRAYSCALE to cv2.IMREAD_COLOR, reran the CreateData routines, then tried to run the NeuralNetwork creation program, but that then fails with error:

I am following a tutorial for TensorFlow and I am having problems during the model prediction phase.

The final bit of code is :

I am trying to make a simple Image Classifier using Tensorflow. From here https://medium.com/@linjunghsuan/create-a-simple-image-classifier-using-tensorflow-a7061635984a

I am using Anaconda2 on Windows 10 (64bit) Packages used The following NEW packages will be INSTALLED:

I'm very new to Azure IoT Edge and I'm trying to deploy to my Raspberry PI : Image Recognition with Azure IoT Edge and Cognitive Services but after Build & Push IoT Edge Solution and Deploy it to Single Device ID I see none of those 2 modules listed in Docker PS -a & Iotedge list And when try to check it on EdgeAgent Logs there's error message and it seems EdgeAgent get error while creating those Modules (camera-capture and image-classifier-service)

I've tried : 1. Re-build it from fresh folder package 2. Pull the image manually from Azure Portal and run the image manually by script

I'm stuck on this for days.

in deployment.arm32v7.json for those modules I define the Image with registered registry url :

enter image description hereso I try to do this macOS tutorial to build an image classifier with tensorflow on a Windows PC, therefore the following prompt doesn't work in the Windows cmd:

I am trying to train a 2D neural network using keras. I have a weird error message, "ValueError: setting an array element with a sequence." when I try to use model.fit function in keras. Specifically, the error says that my "tensor_train_labels" is a sequence instead of an array. But my labels are indeed numpy arrays (not a sequence). I am not sure why does keras complain about it ?

I am following this tutorial for building my network

I am trying to feed my image roi into the Tensorflow classifier I took from here. The idea is to first run a simple filter, get rectangle candidates, and then check (using the network) whether each rectangle(roi) is actually what I am looking for.