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
0
votes
1 answer

Detecting small objects with MobileNet and Faster RCNN

I'm working on object detection of various sorts of animals using the Tensorflow Object Detection API. In the past I successfully applied MobileNet v1 to various settings and I used to be happy with the results. Now, I encountered a problem with a…
zimmermc
  • 623
  • 2
  • 6
  • 13
0
votes
2 answers

ValueError: not enough values to unpack (expected 2, got 1) in MaskRCNN

I am trying to train my own dataset with MaskRCNN, I got the code from https://github.com/matterport/Mask_RCNN and I started training my dataset with this framework I got this error. I tried training another dataset of some other person then the…
bh.gaurang
  • 1
  • 1
  • 3
0
votes
1 answer

Table Detection Task (TableBank & Detectron ) : UnicodeDecodeError: 'ascii' codec can't decode byte 0x80 in position 0: ordinal not in range(128)

I have been trying to run a python script to test a pretrained model (ResNeXt-101) and visualize the performance of a Table Detection task proposed by TableBank. The authors pretrained the model using the Detectron library (Facebook AI Research’s…
Arij SEDIRI
  • 2,088
  • 7
  • 25
  • 43
0
votes
2 answers

keras FRCNN training error message: Exception: 'a' cannot be empty unless no samples are taken

I am using this implementation of FRCNN for training on my dataset: https://github.com/kbardool/keras-frcnn during training I get random exceptions with no stack trace: 708/1000 [====================>.........] - ETA: 289s - rpn_cls: 0.1376 -…
Stepan Yakovenko
  • 8,670
  • 28
  • 113
  • 206
0
votes
1 answer

Is there any way to modify available TensorFlow models architecture (such as ssd or fast r-cnn) so it is optimized for only one object detection?

I am new to Machine Learning and TensorFlow so I'm sorry and please correct me if my understanding is wrong. I have this project, developing a real time traffic-light detection with TensorFlow. I've been working with pre-trained TensorFlow models…
Fransiska
  • 43
  • 4
0
votes
1 answer

Object detection training on large images

Trying to detect number plates by using faster RCNN on the images 4096 by 8192 pixels. Instead of resizing for training I have cropped some parts of the image and labeled the number plate and trained, This way it's working but It cannot detect on…
Profstyle
  • 434
  • 4
  • 20
0
votes
1 answer

RuntimeError: Failed to parse Dictionary from the input stream

I'm completely new to cntk. I recently installed cntk 2.7 (GPU version) on my pc (windows 10,i5-7200U CPU) with GeForce 940MX GPU. I'm trying to set up cntk and the faster rcnn object-detection example provided in the link…
Abhishek Kumar
  • 1
  • 3
0
votes
1 answer

What is the difference between test and validation specifically in Mask-R-CNN?

I have my own image dataset and use Mask-R-CNN for training. There you divide your dataset into train, valivation and test. I want to know the difference between validation and test. I know that validation in general is used to see the quality of…
Mob
  • 409
  • 1
  • 5
  • 14
0
votes
1 answer

How do I align dimensions in Keras CNN so the output matches custom loss function?

I am having trouble getting this model to compile. I am trying to implement a VGG16 but I will be using a custom loss function. The target variable has a shape of (?, 14, 14, 9, 6) where we only use binary crossentropy on Y_train[:,:,:,:,0] then…
Collin Cunningham
  • 729
  • 8
  • 20
0
votes
1 answer

Why faster-rcnn ssd use 3x3 filter to predict box position and class label?

I am reading the faster-rcnn and ssd code for object detection. The prediction layer use the 3x3 filter to predict box position and class label. Why not use 2x2 filter or 4x4 filter or 5x5 filter to predict them?
tidy
  • 4,747
  • 9
  • 49
  • 89
0
votes
1 answer

How to create a loss plot from loaded weights? (model.load_weights) How to add model.load_weights to history?

I would like to create a loss. (plot) I use Mask-RCNN. I loaded a weights from my model. But I can't create a loss function. I got error: 'Model' object has no attribute 'history' model = modellib.MaskRCNN(mode="training", …
Badum
  • 70
  • 1
  • 1
  • 10
0
votes
1 answer

How to divide in half pydicom files (image) using python?

I have a lot of images (pydicom files). I would like to divide in half. From 1 image, I would like 2 images: part left and part right. Input: 1000x1000 Output: 500x1000 (width x height). Currently, I can only read a file. ds =…
James_Hames
  • 59
  • 1
  • 1
  • 7
0
votes
1 answer

Tensorflow object detection train_config file error

So I'm trying to retrain a fast_rcnn object detection model, with just one class, which I've attempted to run both locally (on a VM) and through ML engine. I keep running into the same error in regards to the train_config file however, which is an…
Bobbi
  • 1
  • 2
0
votes
0 answers

Exporting my Tensorflow model and code to a different PC

I have referred to a number of tutorials and built an object detection model using Faster-RCNN on an Anaconda Virtual Environment. Now I want to show case this model, and find problem when I run it on a different system without Anaconda, I try…
Ramandeep Singh
  • 1
  • 5
-1
votes
0 answers

step by step understanding approximate joint training method #192

i don't understand exactly approximate joint training method. i know RPN and detector merged as a one network during training. the forward path is started pre trained conv network and pass from RPN and finally arrives to fast rcnn layers. loss is…
saeed ni
  • 1
  • 1
1 2 3
…
22 23