Object detecion with 10 lines of code


#1

This is a good article. Does anyone have a feel on how easy it would be to port to Julia?
Looking at the github it makes use of many libraries which are already available in Julia


#2

Looks like this is implemented in Keras. You could give Keras.jl a try (https://github.com/ayush1999/Keras.jl). Karas has a model.to_json method to serialize a model to JSON. As long as the Keras model doesn’t have any Lambda layers you should be able to import it to Flux.jl using Karas.jl.


#3

ImportError Traceback (most recent call last)
in ()
----> 1 from imageai.Detection import ObjectDetection
2 import os
3
4 execution_path = os.getcwd()
5

~\Anaconda3\lib\site-packages\imageai\Detection_init_.py in ()
----> 1 import cv2
2
3 from imageai.Detection.keras_retinanet.models.resnet import resnet50_retinanet
4 from imageai.Detection.keras_retinanet.utils.image import read_image_bgr, read_image_array, read_image_stream, preprocess_image, resize_image
5 from imageai.Detection.keras_retinanet.utils.visualization import draw_box, draw_caption

~\Anaconda3\lib\site-packages\cv2_init_.py in ()
1 import importlib
2
----> 3 from .cv2 import *
4 from .data import *
5

ImportError: DLL load failed: The specified module could not be found.


#4

@Ponnoss Are you wanting to implement this in Python?
I am not familiar with Python on Windows 10 but it looks like you need to use Anaconda to install the data package