Stack Overflow
Stack Overflow

Questions tagged [mask-rcnn]

62 questions
0
votes
1 answer

Poor Mask RCNN prediction

I am using a version of the Matterport MRCNN repository to classify 2 objects (lets say dog & cat) trained with ~5k images (1024x1024) using the mask_rcnn_coco.h5 weights for transfer learning. I am wondering if I am doing something wrong, need to…
1337nerd
  • 33
  • 6
0
votes
1 answer

Instance Segmentation Using Mask R-CNN on Custom Dataset IndexError

I am working on semantic segmentation and I came across Instance Segmentation Using Mask R-CNN on Custom Dataset by Code With Aarohi. I met an error. This is the snippet of the code related to the error: def load_mask(self, image_id): …
Lim Cheng Wei
  • 11
  • 3
0
votes
0 answers

Save only the Backbone FPN from MaskRCNN for conversion to onnx format

I have trained a MaskRCNN model successfully and now I am trying to save each of its stages (backbone with fpn, ROI classifier, Mask Head and RPN Head) in order to convert them to ONNX format. But it is not quite clear to me how I can decompose the…
isaac.af95
  • 113
  • 7
0
votes
0 answers

Skin lesion segmentation MaskRCNN error (bool index does not match)

i have a task of using MaskRCNN to do a skin lesion segmentation. I have my work on my github but i have an error on cell 22 when training the model. https://github.com/leahcimali/Skin-cancer-segmentation/blob/main/Project%20Mask.ipynb Knowing that…
Michael
  • 11
  • 2
0
votes
0 answers

System exit 1 error after obtaining NaN losses from finetuning Mask R-CNN in Pytorch

I am following this tutorial from Pytorch for Finetuning a pre-trained model on my own dataset. I have my annotation in the COCO format in a json file, so, I first implemented the dataloader as follows: import torch import json from…
Abdelrahman Youssef
  • 23
  • 4
0
votes
0 answers

Reduce annotations from COCO json file mask rcnn

I want to train my mask rcnn model on 4 classes. ClassA,ClassB, ClassC. Class A has 16000 annotations while classB and ClassC has 5009,and 3000 respectively. I want to reduce the annotations of ClassA to 8000 only. How can I do this in Coco json…
champ
  • 1
  • 2
0
votes
0 answers

fast-cnn model - images with no labels in the training data

How can I modify the example in the "Object Detection FasterRCNN Tutorial" (https://www.kaggle.com/code/pdochannel/object-detection-fasterrcnn-tutorial) to include empty labeled images in the training data? I want to be able to handle cases where…
Petr
  • 1,606
  • 2
  • 14
  • 39
0
votes
0 answers

Mask RCNN with custom classes

after dealing with the compatability issues with Mask RCNN I am working now on training the model on my custom classes with the annotations json being in Coco-style. class modelConfig(Config): NAME = "my_coco" NUM_CLASSES = 1 + 6 STEPS_PER_EPOCH =…
ArieAI
  • 354
  • 1
  • 12
0
votes
0 answers

required libraries works only from second time on Сolab when using TF2 for mask rsss

could you please help me with following problem: I used TF2 for MaskRCNN. The first cell gives such error. I did it looking here first cell !apt-get update !pip3 install scikit-image==0.16.2 !pip3 install opencv-python !pip3 install…
Fatikha Work3
  • 1
0
votes
0 answers

Mask-RCNN ,To train the labeled data, I want to label using coordinates that contain numbers below the decimal point

{"shape_attributes":{"name":"polygon","all_points_x":[[977, 977, 977, 976, 976, 975, 974], {"shape_attributes":{"name":"polygon","all_points_y":[[403, 403, 403, 403, 403, 402, 402] If I remove the number below the decimal point and change it to an…
전아현
  • 1
0
votes
0 answers

Nan Loss during training - MaskRCNN

I am training a custom Dataset sample_data where each image annotation is in the Pascal VOC XML format. When training the MaskRCNN model from the matterport repo for TensorFlow 1.15 and the maskrcnn for Tensorflow 2.2.0 config for the matterport…
Mehathab A
  • 1
  • 2
0
votes
0 answers

Perform Instance Segmentation Using Mask R-CNN

i just following 'Perform Instance Segmentation Using Mask R-CNN' example URL : "https://kr.mathworks.com/help/vision/ug/example-InstanceSegmentationUsingMaskRCNNDeepLearningExample.html" I have download the file(instances_train2014.json,…
big rabbit
  • 1
0
votes
2 answers

How to make predictions with Mask R-CNN and python 3.10

My problem: I have weights for a Mask R-CNN Model, which has been trained using python 3.7 and tensorflow 1.13.1. I can use this environment to make predictions. I am able to reproduce those predictions using python 3.8 and loading the weights with…
Valecz
  • 61
  • 6
0
votes
2 answers

AttributeError: module 'tensorflow' has no attribute 'placeholder'

AttributeError: module 'tensorflow' has no attribute 'placeholder' config = CustomConfig() model = modellib.MaskRCNN (mode= "training", config=config, model_dir=DEFAULT_LOGS_DIR) weights_path = COCO_WEIGHTS_PATH # Download weights file if not…
Magic
  • 1
0
votes
0 answers

Run ballon.py from Mask_RCNN project

I am trying to run balloon.py from https://github.com/matterport/Mask_RCNN on Pycharm, using tensorflow 2.11 and python 3.8. I have been able to make changes to model.py to accomodate tensorflow 2.11. Now, when I try to run balloons.py from Pycharm,…
Rina Tse
  • 61
  • 5
1 2
3
4 5