Stack Overflow
Stack Overflow

Questions tagged [caffe2]

Caffe2 is an open-source deep learning framework, which is developed and maintained by Facebook, and is based on the Caffe framework.

Caffe2 is a deep learning framework, which is based on the framework. It is developed and maintained by Facebook, and released under the Apache 2.0 license, on GitHub.

Caffe2 is an improved / redesigned version of Caffe. A presentation by Caffe2's lead developer Yangqing Jia, held at CVPR 2015, shows some of the consideration of the redesign.

Useful links

116 questions
0
votes
1 answer

caffe2 obtain learning rate: Can't find blob: gpu_0/conv1_w_lr

the code to obtain the learning rate in resnet50_train.py is as follows: learning_rate = workspace.FetchBlob(prefix + '/conv1_w_lr') and when I run the code, errors occured: Traceback (most recent call last): File …
sq g
  • 1
0
votes
1 answer

In Caffe2, is there any caffemodel that deals with the chatbot conversation

In Caffe2, is there any caffemodel that deals with the chatbot conversation. Is there any model that helps to work with the text classification / analysis Is there any DNN example / sample that deals with the text statements as given in the Caffe2…
Pandu Balraj
  • 1
0
votes
1 answer

Food101 SqueezeNet Caffe2 number of iterations

I am trying to classify the ETH Food-101 dataset using squeezenet in Caffe2. My model is imported from the Model Zoo and I made two types of modifications to the model: 1) Changing the dimensions of the last layer to have 101 outputs 2) The images…
Shaun
  • 3
  • 2
0
votes
1 answer

Do all Caffe2 projects have to be under caffe2 install folder?

I've successfully installed Caffe2 on my TX2 with jetPack by NVIDIA. I am trying to figure out if I could make a folder that's not under my caffe2 installation folder (where caffe2 is installed) and make a new cmake project. How does one connect…
Sky Walker
  • 23
  • 4
0
votes
2 answers

Memory Management in Caffe2

I am new to caffe2 and I wanted to know how does the caffe2 framework stores the models in the CPU or the GPU memory and how that is maintained. I have tried reading its github code but nothing concrete so far. Thanks for the help :) :)
Abhishek Saroha
  • 1
  • 2
0
votes
1 answer

Explanation of template statement in Caffe2 InputIsType method

The Caffe2 framework includes the following code in the file caffe2/core/operator.h: template inline bool InputIsType(int idx) { return inputs_.at(idx)->template IsType(); } I do not understand the third line of this code…
user3132300
  • 3
  • 2
-1
votes
1 answer

How to build/install caffe2 in windows?

I have tried setting up caffe2 in windows 10 by cloning the pytorch repo and trying to build from source since binaries are not available for windows platform. But whenever I run the build_windows.bat file in pytorch/scripts, I end up getting the…
RrR-
  • 1,251
  • 3
  • 15
  • 32
-1
votes
1 answer

when git clone caffe2 , return thirtparty eigen repository error:

when I excuted git clone from caffe2, return thirtparty eigen repository error: git clone --recursive https://github.com/caffe2/caffe2.git .... remote: Repository not found. fatal: repository 'https://github.com/RLovelett/eigen.git/' not found
Lao Jiang
  • 1
  • 2
-1
votes
1 answer

How to convert Caffe trained model and parameters to directly be used for inference in caffe2?

I have a trained caffe model on a CPU desktop. I want to port it mobile platform to do inference using Caffe2. Any insights into how should I go about with it? Do the scripts that are provided by Caffe2 allow for conversion of the model and reuse of…
Srujana
  • 1
-2
votes
1 answer

How to reject false alarm in object detection using SSD?

I used SSD for my object detection. But there are some false detection from some other objects in the image. That is happening consistently from same objects. So is there a way to reject those components in training?
batuman
  • 7,066
  • 26
  • 107
  • 229
-4
votes
1 answer

Developing a customized caffe-based Convolutional Neural Network from scratch

I like to develop a new Convolutional Neural Network from scratch and here found a discussion how to use pre-trained model for a new network. There are four categories and if the training image size is small and data similarity is low, we need to…
batuman
  • 7,066
  • 26
  • 107
  • 229
1 2 3 4 5 6 7
8