Faster-RCNN is a very common Regional Convolutional Neural Network architecture that detects and recognizes objects in images in a single forward pass
Questions tagged [faster-rcnn]
332 questions
2
votes
1 answer
ImportError: cannot import name 'device_spec' from 'tensorflow.python.framework'
When i try to run
python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config
command this error pops out.
(tensorflow1.13)
C:\tensorflow1\models\research\object_detection>python…
saydarov
- 33
- 1
- 7
2
votes
1 answer
grayscale input for keras InceptionV3
I have made this network which seems to work ok.
datagen = tf.keras.preprocessing.image.ImageDataGenerator(
#zoom_range=0.2,
#shear_range=0.2,
#rotation_range=10,
rescale=1/255,
validation_split=0.2,
# other…
Michael Hansen
- 237
- 2
- 8
2
votes
1 answer
Save the best model trained on Faster RCNN (COCO dataset) with Pytorch avoiding to "overfitting"
I am training a Faster RCNN neural network on COCO dataset with Pytorch.
I have followed next tutorial:
https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html
The training results are as follows:
Epoch: [6] [ 0/119] eta: 0:01:16 …
Jose David
- 39
- 9
2
votes
0 answers
R-CNN Keras Implementation
I am implementing R-CNN in keras using this article https://towardsdatascience.com/step-by-step-r-cnn-implementation-from-scratch-in-python-e97101ccde55
In this article, The image is passed to the selective search and the proposed regions are…
user12914245
2
votes
1 answer
Memory Error (OOM) while testing Tensorflow Object Detection API
I trained faster_rcnn_nas model with my custom dataset (resized images 1280x1080). My GPU is Nvidia Quadro P5000 and I can test the model on this computer.
When I test with GTX 1060 it crashes and gives memory error. But when I test pre-trained…
Emre Tatbak
- 103
- 3
- 11
2
votes
1 answer
PyTorch FasterRCNN TypeError: forward() takes 2 positional arguments but 3 were given
I am working on object detection and I have a dataset containing images and their corresponding bounding boxes (ground-truth values).
I actually have built my own feature extractor which takes an image as input and outputs a feature map(basically an…
Jitesh Malipeddi
- 2,150
- 3
- 17
- 37
2
votes
0 answers
Mask R-cnn / UnboundLocalError: local variable 'image id' referenced before assignment
I've been trying to run Mask R-CNN on a small custom dataset (images + .json polygon data, converted into binary masks) on Google Colab (the script is a mix between different tutorials using the Mask R-CNN/ Matterport repo on github). Everything…
thepandrea
- 21
- 2
2
votes
0 answers
Object Detection: Aspect Ratio and Scale of Anchor Boxes
I am working on an object detection problem on my own dataset. I want to figure out the scale and aspect ratio that I should specify in the config file of Faster RCNN provided by Tensorflow object detection api. The first step is image resizer. I am…
Aashish Kumar
- 21
- 2
2
votes
0 answers
PyTorch tensor.to(device) for a List of Dict
I am working on an image object detection application using PyTorch torchvision.models.detection.fasterrcnn_resnet50_fpn. As indicated by the documentation, during training phase, the input to fasterrcnn_resnet50_fpn model should be:
- list of image…
tommyc
- 61
- 2
- 5
2
votes
1 answer
How to define inner polygon in coco dataset?
I'm looking to understand how to define inner or interior polygon in segmentation part of coco dataset
I'd like to teach the convolution network to recognize holes in building polygons
Example of the polygon with hole
Toren
- 6,648
- 12
- 41
- 62
2
votes
1 answer
Mask-RCNN/TensorFlow:Will different image formats (jpg, png) affect the training results of Mask-RCNN?
I used Mask-RCNN and Tensorflow in a project. I have completed many trainings in the past.
In the recent one, I found loss curve having a large amplitude of shock in tensorboard. I changed some settings such as batch_size in a small range but it's…
Zhengfei Xin
- 35
- 3
2
votes
0 answers
MultiLabelling to recognize subclasses for multi object detection in images
I'd would like to classify objects (dices in particular) with a method based on YOLO, or Faster RCNN. I'm using my own database, and I would like to label my images in order to pass it to my model. However, I was thinking of using LabelImg to do so,…
meira
- 21
- 2
2
votes
1 answer
AttributeError: module 'tensorflow._api.v1.compat.v1.nn' has no attribute 'avg_pool2d'
can some help me with this?
File "C:\tensorflow1\models\research\slim\nets\mobilenet\mobilenet.py", line 397, in
def global_pool(input_tensor, pool_op=tf.compat.v1.nn.avg_pool2d):
AttributeError: module…
Nur Fe
- 47
- 1
- 6
2
votes
0 answers
Showing predicted boxex in an RPN (Tensorflow Faster-RCNN)
I’m stuck in training a model for the recognition of characters on images.
What I’m currently doing is trying to recognize letters in a relatively small image (700x50) by using the pre-defined faster-rcnn from the TensorFlow object detection…
Selim Berisha
- 21
- 2
2
votes
1 answer
how to reduce input size for mask-RCNN trained model while running prediction on google cloud platform
I am trying to use Google AI Platform prediction to perform object recognition using Mask RCNN. After spending close to two weeks, I was able to:
find out how to train on Google Cloud
convert the model from h5 to the SavedModel format required by…
akshay pai
- 122
- 12