Stack Overflow
Stack Overflow

Questions tagged [faster-rcnn]

Faster-RCNN is a very common Regional Convolutional Neural Network architecture that detects and recognizes objects in images in a single forward pass

332 questions
-1
votes
2 answers

2 Faster R-CNN models with different backbones, produce the same results during inference

Im using a python program from this tutorial. I've copied it as is and made changes to directories and label list so that the program takes in my dataset. The first Faster R-CNN model was trained with the ResNet50 backbone. I have trained it, I have…
Rudy Robot
  • 1
  • 1
-1
votes
1 answer

Limited number of bounding boxes in fasterRCNN PyTorch

I use a pre-trained fasterRCNN from PyTorch to detect small obstacles in a 4k image. Currently I am facing some issues with false negatives, so objects are not detected. I recognized that the number of detected objects per image is always 100, even…
PeterAlgoMaker
  • 11
  • 3
-1
votes
1 answer

faster r-cnn test all images in folder

I have trained my model using faster-rcnn on my computer. As you know , using script you can only test 1 image. But I want to test all images in my test folder. I have to write a code (using loops) which enables me to do that. Is there anyone can…
Rainy Day
  • 9
  • 3
-1
votes
2 answers

Getting Error too many indices for tensor of dimension 3

I am trying to Read an Image using GeneralizedRCNN, Input shape is given as a comment with code. The problem is I am getting an error while tracing the model with input shape. The error is : > trace = torch.jit.trace(model, input_batch) line…
Honey Kumar
  • 1
  • 1
  • 2
-1
votes
1 answer

How to implement RPN in Faster RCNN for object detection?

I am trying to implement the Faster RCNN on identifying the airplane from the image. I stuck at implementing Region Proposal Network(RPN). How can I implement RPN and train them to produce bounding box proposal using python script?
Madan Parajuli
  • 3
  • 3
-1
votes
1 answer

How to predict Faster RCNN model in batches?

I have a trained RCNN (Keras-Retinanet) model and I could predict only one image at a time. boxes, scores, labels = model.predict_on_batch(np.expand_dims(image, axis=0)) Full script is here. Is there a way to predict multiple images at a…
RedFox
  • 1,158
  • 2
  • 15
  • 28
-1
votes
1 answer

Object Detection without labels / annotation

Let say I have 3 images (an apple, an orange, a banana) and another 1000 arbitrary images. What I want to do is to see if those 1000 arbitrary images contain object(s) similar to the former 3 images, if yes, draw a bounding box to indicate those…
Trevor. W
  • 451
  • 1
  • 5
  • 13
-1
votes
2 answers

How to use FasterRCNN Openimages v4?

I can't seem to find any documentation on how to use this model. I am trying to use it to print out the objects that appear in a video any help would be greatly appreciated I am just starting out so go easy on me
Ahmed Salah
  • 27
  • 7
-1
votes
1 answer

AttributeError: module 'tensorflow' has no attribute 'log' during Mask RCNN implementation

I tried changing log to math.log and downgraded tensorflow version to 1.4 But still got the error.Can someone Please help.Thank you. AttributeError: in user code: /content/Mask_RCNN/mrcnn/model.py:390 call * roi_level = log2_graph(tf.sqrt(h *…
radha garapati
  • 1
  • 1
-1
votes
1 answer

What are pretrained weights and initialization weights in Mask R-CNN?

I'm trying to train Mask R-CNN for instance segmentation. Where are some available pretrained models. Are these weights for the whole neural net or only for encoder/backbone (for instance resnet50)? Also there's initializations weights using…
Kenzie
  • 1
-1
votes
1 answer

object detection algorithm outputs an image with no bounding boxes around the detected objects after testing the algorithm

my partner and I are have created a modified faster rcnn algorithm and it doesn't seem to have any bounding boxes when it outputs an image after testing the algorithm but it only outputs the Mean Average Precision. so far what I've tried doing is…
VinceG
  • 77
  • 1
  • 2
  • 10
-1
votes
1 answer

(0) Unknown: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize

Here i am using mask_rcnn for object detection. The code was functioning without error but now I am getting the following error. code : Testing - 1 # 1 - 200 images testing # Load a random image from the images folder file_names =…
Amuthalingeswaran C
  • 7
  • 4
-1
votes
1 answer

How to pass image batches as locals to profile.runctx?

I want to send a batch of images to profile.runctx Ex profile.runctx('print (inference(image_batch,batch_size)); print()', globals(), {'image_batch':'how to send image batch?','batch_size':128}) I have a function…
Rehoboth
  • 43
  • 2
  • 6
-1
votes
1 answer

training and prediction module API do not run same time using flask

I used Mask_RCNN module with flask When I do not add K.clear_session() then I face this error in training and prediction module error Cannot interpret feed_dict key as Tensor: Tensor Tensor(\"Placeholder:0\", shape=(7, 7, 3, 64), dtype=float32) is…
RAJAN NAGPAL
  • 1
-2
votes
1 answer

What is the difference between (ResNet50, VGG16, etc..) and (RCNN, Faster RCNN, etc..)?

I am confused with the difference between Kearas Applications such as (VGG16, Xception, ResNet50 etc..) and (RCNN, Faster RCNN etc...). Beause in some places it is mentioned that ResNet50 is just a feature extractor and FasterRCNN/RCN, YOLO and SSD…
Muntha
  • 41
  • 1
  • 7
1 2 3
…
22
23