Stack Overflow
Stack Overflow

Questions tagged [mask-rcnn]

62 questions
0
votes
0 answers

While testing the model on test dataset of MaskRCNN, the result shows blank images and shows the low contrast image

I am training and testing a MaskRCNN model for detecting the anomaly in patterns of brain. The image size is 112*112 (3 channels) and format is .dicom. While testing the model on the actual radiographic images, the result shows blank image with the…
Gourav Gupta
  • 15
  • 3
0
votes
0 answers

Resnet50 in MaskRCNN

I want to train my mask rcnn model on pretrained model resnet50. What part in the code do I need to change? Currently, it has option of coco, imagenet and last def load_training_model(config): model = modellib.MaskRCNN(mode="training",…
champ
  • 1
  • 2
0
votes
0 answers

Display a few images from the training dataset

I am trying to Display a few images from the training dataset (Mask RCNN) code dataset = dataset_train image_ids = np.random.choice(dataset.image_ids, 4) for image_id in image_ids: image = dataset.load_image(image_id) mask, class_ids =…
Manas Wakchaure
  • 1
0
votes
1 answer

How is it possible to have different input image sizes in Detectron2?

I am using Detectron2 (Mask-RCNN Model) and passed by: _C.INPUT.MIN_SIZE_TEST = (800, 832, 864, 896) _C.INPUT.MAX_SIZE_TEST = 1333 How is it possible to have different input image sizes? How are they entered into the model and Shouldn't the model…
Nabil Miri
  • 1
0
votes
0 answers

How to create a Keras model from saved weights without a config JSON (Mask-RCNN)

I'm trying to use the TACO dataset GitHub Repository to get a functional neural network, and I downloaded pre-trained weights from here. I understand that the .h5 file contains only the weights and not the architecture of the model itself. I am…
python-beginner
  • 1
  • 1
0
votes
2 answers

No module found error while importing python in notebook

I want to acess m_rcnn.py file in jupyter notebook. The folder structure is as follows collab_mask_rcnn(working directory). Inside this workinhg directory i have a folder name maskrcnn_colab and inside this maskrcnn_colab folder i have another…
Kumar
  • 55
  • 3
0
votes
0 answers

Visualize output from Mark RCNN

I followed this tutorial: https://github.com/lih0905/PyTorch_Study/blob/master/8)%20TorchVision%200.3%20Object%20Detection%20finetuning%20tutorial.ipynb and how can you see there is output images at the end of page and it's pretty good. Now I also…
Leon
  • 33
  • 7
0
votes
1 answer

How to extract a segmented object or change the background of the original image?

I am doing a detection with Mask R-CNN of one model available at Train Mask R-CNN for Image Segmentation. Code I # Load Image img = cv2.imread("/content/image.jpg") test_model, inference_config = load_inference_model(1,…
Diego A
  • 155
  • 7
0
votes
0 answers

MaskRCNN should find exactly one element

I trained a maskrcnn-model with matterport with one class to detect. It worked. Now I want to predict some unseen images. I know that the object is present on each image and that it appears only once per image. How do I use my model to do so? An…
SchwarzbrotMitHummus
  • 69
  • 1
  • 8
0
votes
0 answers

MaskRCNN (matterport) - BBox from utils.extract_bboxes(mask), but it included the objects that should be independent

this is my first time asking a question here, and I'm not an English native speaker. So please forgive my poor English. I used matterport/MaskRCNN to train a model that can detect activities on the beach, like swim, surfing, and…
WeiCC
  • 1
0
votes
1 answer

Object detection with MaskRCNN. Why is mean average Precision(maP) equal to 0 when training with Json dataset?

While I was installing the Maskrcnn on Windows10 by following the video https://www.youtube.com/watch?v=QntADriNHuk&t=1177s (286 - Object detection using Mask RCNN: end-to-end from annotation to prediction), every steps look fine until doing the…
Yangyang
  • 1
0
votes
0 answers

Detections are way off and mAP is always zero with M-RCNN training

I'm attempting to apply Matterport's Mask-RCNN setup to my own data, but despite all of the great examples of impressive detections I've seen out there, I'm really struggling to get results that are at all promising, and so I'm suspecting that…
lusk
  • 541
  • 5
  • 21
0
votes
0 answers

The model cannot be trained well by MASK RCNN

I am using MRCNN in python to train 20 images (with annotated images info saved as json file) for object detection. The problem is that at the best case the loss is around 4 which it shows that the model has not learned well (the loss fluctuates a…
user15167312
  • 1
0
votes
1 answer

Performance drop when converting Mask RCNN to uff format

My goal is to deploy a Mask RCNN model trained with the well known Matterport's repo with Nvidia deepstream. To do so, first I have to convert the generated .h5 model into a .uff. This operation is decribed here. After the conversion, I have run the…
Aure
  • 31
  • 1
  • 5
0
votes
0 answers

warning while training maskrcnn using detectron

I am training mask rcnn using detectron framework and getting below…
Radhi
  • 6,289
  • 15
  • 47
  • 68
1 2 3
4
5