ModelLib

# Create model in inference mode import tensorflow as tf from tensorflow import keras with tf.device(DEVICE): model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config)`

# load the last best model you trained # weights_path = model.find_last()[1] custom_WEIGHTS_PATH = '/home/unni/my_project_work/car-damage-detection-using-CNN-master/logs/scratch20190612T2046/mask_rcnn_scratch_0013.h5' # Load weights print("Loading weights ", custom_WEIGHTS_PATH) model.load_weights(custom_WEIGHTS_PATH, by_name=True)`

This is the error AttributeError: in user code:

Running the code below - trying to implement the maskrcnn with opencv and my webcam.

When I set PROCESS_IMG = False, the output is fine, shows webcam input as well as FPS (if I set it to false).

I tried to comment out the line s = masked_image and below and every 4-5 seconds I would get a refresh of the webcam as well as a proper maskrcnn output overlaid on top (which is what I want).

Not assuming I'm going to get 60fps by any means, 0.2fps would be fine.

I have a Django application which it's deployed to Amazon Elastic Beanstalk(Python 3.7 running on 64bit Amazon Linux 2/3.0.3). I have installed anaconda and pythonocc-core package by creating a 10_anaconda.config file in .ebextensions folder.

10_anaconda.config;

I'm trying to crop segmented objects outputed by an MASK RCNN the only problem is that when i do the cropping i get the segments with mask colors and not with their original colors.

Here's the outputed image with the segments :

and here's one segment (we have 17 segments in this image ) :

as you can see , we have the segment with the mask color and not the original color.

here's the code that i'm using :

I am a newbie ML learner and trying semantic image segmentation on google colab with COCO data format json and lots of images on google drive.

update

I borrowed this code as a starting point. So my code on colab is pretty much like this. https://github.com/akTwelve/tutorials/blob/master/mask_rcnn/MaskRCNN_TrainAndInference.ipynb

/update

I am splitting an exported json file into 2 jsons (train/validate with 80/20 ratio) every time I receive new annotation data. But this is getting tiring since I have more than 1000 annotations in a file and I do it manually with replace function of VS code.

Is there a better way to do this programatically on google colab?

So what I like to do is rotating annotation data without spitting a json file manually.

Say, I have 1000 annotations in ONE json file on my google drive, I would like to use the 1-800 annotations for training and the 801-1000 annotations for validating for the 1st train session, then for the next train session I would like to use the 210-1000 annotations for training and 1-200 annotations for validating. Like selecting a part of data in json from code on colab.

Or if I can rotate the data during one train session (K-Fold Cross Validation?), that is even better but I have no clue to do this.

Here is parts of my code on the colab.

Loading json files

I want to launch mask-rcnn model from visualize_cv2.py. My goal is train only on 1 element from class_names - person. For this I create class_names1(added full code from this python file for better understanding):

I wanted to perform multi-gpu inference using tensorflow/Keras

this is my prediction

I'm importing files from the following folder inside a python code:

I am trying to run the Keras implemention of Mask_RCNN in inference mode. It is basically running this code demo.ipynb

But when I run it, I get the following error on model creation :