caffe

问题 I am trying to build caffe (libcaffe,pycaffe) on windows using Visual studio. I downloaded the caffe-master project from below link Caffe for windows using visual studio 2015 and open the solution caffe in it. enabled python support true to build some nuget-packages were missing so restore them. for this followed the link How to install caffe in windows in five minutes try to build the project but getting following errors: C2059 syntax error: 'constant' (compiling source file ..\..\src\caffe

问题 I'm trying to create a single multi-class and multi-label net configuration in caffe. Let's say classification of dogs: Is the dog small or large? (class) What color is it? (class) is it have a collar? (label) Is this thing possible using caffe? What is the proper way to do so? Just trying to understand the practical way.. After creating 2 .text files (one for training and one for validation) containing all the tags of the images, for example: /train/img/1.png 0 4 18 /train/img/2.png 1 7 17

问题 I noticed how the Caffe MNIST example prototxt file allows for up to 64 images to be passed to the network at a time. Is there a limit for how high I can set this number? Could I (for example) set this number to 200 or even 500 so that I can accept up to 200/500 images at a time without it impacting the predictions negatively? 回答1: The only limit is your machine's memory: When caffe loads the model it allocates memory for all the parameters and all the intermediate data blobs. The more images

问题 I want to learn how to write caffe python layers. But I only find examples about very simple layers like pyloss. How to write python caffe with trainable parameters? For example, how to write a fully connected python layer? 回答1: Caffe stores the layer's trainable parameters as a vector of blobs . By default this vector is empty and it is up to you to add parameters blobs to it in the setup of the layer. There is a simple example for a layer with parameters in test_python_layer.py. See this

问题 During the process of making a lmdb file,we are supposed to make a train.txt and val.txt file,i have already made a train.txt file which consists of the image name space its corresponding label.Ex image1.JPG 0. Now that i have to make the val.txt file im confused as to how do i give it its corresponding values since it is my test data and i am hoping to predict those.Can anyone tell me what this val.txt file is and what is it supposed to be doing. 回答1: You are confusing test and validation

问题 I'm trying to build Caffe on Ubuntu 14.04 x64 in VirtualBox with openblas in CPU_ONLY mode.(Enviroment install script , Makefile.config ) Also I'm not compiling OpenBlas, but install it via apt-get like sudo apt-get -y install libopenblas-dev , can it be reason of the problem? After I set any of this variables, there is no speed improvement and in htop I see only one CPU utilisation. export OPENBLAS_NUM_THREADS=4 export GOTO_NUM_THREADS=4 export OMP_NUM_THREADS=4 How to check if Caffe use

问题 I am wondering if anyone has tried using compression techniques for their LMDB files? Typically, lmdb files typically do not use any compression. I am wondering if anyone has successfully stored data in an lmdb using jpeg compression on lmdb and then used it for caffe. I need this because I am working on a developer board with very limited storage space. If so, can you please provide steps/code to do this? thanks 回答1: Caffe also supports HDF5 which supports compression. If your dataset is

问题 I successfully compiled Caffe under Ubuntu and started to study how to define and train my own networks. However, I'm having trouble to understand how the convolutional layer produces its output. For example the second convolutional layer (conv2) of the LeNet MNIST tutorial (tutorial, lenet.prototxt) has 20 input images and 50 output images: layer { name: "conv2" type: "Convolution" bottom: "pool1" top: "conv2" param { lr_mult: 1 } param { lr_mult: 2 } convolution_param { num_output: 50

问题 Closed . This question needs to be more focused. It is not currently accepting answers. Want to improve this question? Update the question so it focuses on one problem only by editing this post. Closed 2 years ago . I managed to write numpy arrays to lmdb, howewer solution is far from perfection, but actually my X is just jpg image, so my question is how to directly write jpeg file to lmdb? Seems like pycaffe doing similar thing but it use caffe specific Datum and I need some general solution

问题 I'm trying to build a CNN that classify object in 3 main classes.The three objects consist of a lamborghini , cylinder head and a piece of plane. My data set consists of 6580 images , almost 2200 image for each class.You can see my dataset on google drive dataset. The architecture of my CNN is AlexNet , but I've modified the output of fully connected layer 8 from 1000 to 3. I have used these settings for training test_iter:1000 test_interval:1000 base_lr:0.001 lr_policy:"step" gamma:0.1