Where communities thrive

  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
Repo info
Or implementation of LSTM on road segmentation?
Ramesh uprety
Ramesh uprety
Hello there :)
Rajat Arora
anyone made projects related to Generative Adversarial networks?
Ramesh uprety
Punita Ojha
This message was deleted
Hi, what are some of the best resources to train a network to detect different kinds of bags?
Can someone help me out here? I've been looking into faster RCNN
Aditya Khanna
@rajat1994 I know this message is very late, but I'm experimenting with generative adversarial networks for a project of mine.
Priyabrata Dash
i saw your message on github
did you get a maintainer
Amit Manchanda
Hi everyone, I have been making a list of various topics to read for a newbie in ML/DL along with field/ varied works that have been done using DL. https://github.com/amitmanchanda1995/papers
how are you?
what is the meaning of category image in store database modeling
Pramod Shenoy

hi guys!

I am from Manipal Institute of Technology(India) and I am an Organizer for the college's annual Python Conference-MUPy

I want to invite passionate developers and python experts to be a part of this conference in October and invite proposals if any of you would like to speak or share your experiences. We've had great speakers in our first edition itself. We can arrange for video conferences for people out of India at any convenient time! This will be great chance and platform for you to tell the world about your story and experience and can help budding engineers,innovators and developers to start theirs. PM me if you are interested!

Ramesh uprety
What is the purpose of combining Max pooling with 1x1 convolution ? http://iamaaditya.github.io/2016/03/one-by-one-convolution/
Kiki Rizki Arpiandi
I want to develope computer vision software for recognizing cars on single board computer, what do you thinks is better between tensorflow, caffe, or caffe2
Jairo Cabrera
Hi guys
Could anyone help me with facial recognition please?
I tried using previous models, but they don't work well. I don't know if I am putting data in a wrong way
@promach max pooling is used to zoom out a image and then 1x1 convolution is used to extract information from feature with dimentionality reduction .
Renato Marinho
This message was deleted
@ajithvallabai max pooling is used to zoom out a image ? I do not understand
Renato Marinho
This message was deleted
Renato Marinho
This message was deleted
@meanmee I did that using KITTI dataset and Clockwork Convnets for Video Semantic Segmentation
So afaik C3D can split videos and classify them, but most of the datasets, ucf101, for example, contains widely different classes of action. I am looking to a finer level of details, in the case of football for example, how would one distinguishes a goal shoot and a missed shoot and a free kick etc? C3D can takes me through splitting, but the classification is all messed up. Anyone has any input?
nawal ould amer
Hi everyone, do you know if there are deep learning models that can understand the diagrams images ? let say we have an image that contain two boxes and a link (arrow) between them and the dl model says box linked to box
Ferdinand Fardant
hey..guys..if any one can help me i keep getting 'local unbounded error' when I try to train classification problem. Based on transfer learning.in keras with tensorflow back end... thanks
the logo changed
hi @everyone I'm trying to build up a community for discussions and projects related to python programming , Data Science, AI, ML, Deep Learning, Neural Nets, and related topics we're growing as a community now If you're interested feel free to join in
@OudarjyaS_twitter Going to this link gives 'Invite Invalid' message
I am currently hiring 1-2 individuals to fill a computer vision position, is this the right place to post for that? I am also a bit new to gitter so I am not sure if there are any mods I should contact first.
if anybody is interested with a computer vision position at a funded startup please pm me.
Shubham Verma
I am interested
Hi everyone, I would ask you comment and help on object detection task. I want to recognise electric schematic , do you know if there is papers or idea how to do it
Sumit Sahay
Hii, I need help with some image processing using Keras
Can anyone help me with that?
Hi everyone. Does anyone know lib of heat map
Ammar Chalifah
Hi everyone, I'm a newbie in this field and currently really interested to learn computer vision, especially its application in medical field. Now I'm doing a project to create an object detection model using Faster R-CNN from scratch. Do you have any learning material or source code references that I can see to look how faster r-cnn works under the hood? I've read its paper and countless blog posts, also some github repos but I don't understand the complex implementation. Any suggestions?
Hi ! I am currently working on estimating cost for fixing a car after an accident ( some dents, scratches )using computer vision. We actually have some good results, but to make them better, I would like to go in the direction of reducing reflections from the car body. My MaskRCNN gives a decent results, but we have high value of false positives. Could you point me into the direction of some techniques, libraries, publications in order to reduce number of reflections from a car ?
Hi, everyone can anyone help me with some tutorial on CNN+LSTM.