The mask-rcnn-implementation from codeperfectplus

mask-rcnn-implementation's Introduction

👉 Mask RCNN Implementation on LabelMe Annotations Data 👈

Prepare Data

DataSet Folder Structure

Labelme Annotations tools

- Data_folder
    - train
        - img1.jpg
        - img1.json
        - img2.jpg
        - img2.json
        ...
    - val
        - img3.jpg
        - img2.json
        - img4.jpg
        - img4.json
        ...

Training

# Configuration
# Adjust according to your Dataset and GPU

IMAGES_PER_GPU = 2 # 1
 
# Number of classes (including background)
NUM_CLASSES = 1 + 1 # Background

# typically after labeled, class can be set from Dataset class
# if you want to test your model, better set it corectly based on your trainning dataset

# Number of training steps per epoch
STEPS_PER_EPOCH = 100

The easiest way to get started is to simply try out on Colab:

Training the model on Custom Data

python customTrain.py train --dataset=path_to_Data_folder --weights=coco

ReTraining from Last Checkpoint

python customTrain.py train --dataset=path_to_Data_folder --weights=last

Requirements

Python3.6
Tensorflow-gpu==1.15
keras==2.0.8

For more details check Mask RCNN Repo

mask-rcnn-implementation's People

Contributors

Stargazers

Watchers

mask-rcnn-implementation's Issues

IndexError: index 2848 is out of bounds for axis 0 with size 2848

Hi,
I got the following error during the model training,

Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/mrcnn/model.py", line 1709, in data_generator
use_mini_mask=config.USE_MINI_MASK)
File "/usr/local/lib/python3.7/dist-packages/mrcnn/model.py", line 1212, in load_image_gt
mask, class_ids = dataset.load_mask(image_id)
File "/content/Mask-RCNN-Implementation/customTrain.py", line 211, in load_mask
mask[rr, cc, idx] = 1
IndexError: index 2848 is out of bounds for axis 0 with size 2848

anyone can you have a solution kindly help me to fix an this error.
Thank you

Recommend Projects