caffe

问题 I'm looking for a way that, given an input image and a neural network, it will output a labeled class for each pixel in the image (sky, grass, mountain, person, car etc). I've set up Caffe (the future-branch) and successfully run the FCN-32s Fully Convolutional Semantic Segmentation on PASCAL-Context model. However, I'm unable to produce clear labeled images with it. Images that visualizes my problem: Input image ground truth And my result: This might be some resolution issue. Any idea of

问题 Recently, many deep architectures use "batch normalization" for training. What is "batch normalization"? What does it do mathematically? In what way does it help the training process? How is batch normalization used during training? is it a special layer inserted into the model? Do I need to normalize before each layer, or only once? Suppose I used batched normalization for training. Does this affect my test-time model? Should I replace the batch normalization with some other/equivalent layer

问题 I created a "Python" layer "myLayer" in caffe, and use it in the net train_val.prototxt I insert the layer like this: layer { name: "my_py_layer" type: "Python" bottom: "in" top: "out" python_param { module: "my_module_name" layer: "myLayer" } include { phase: TRAIN } # THIS IS THE TRICKY PART! } Now, my layer only participates in the TRAIN ing phase of the net, how can I know that in my layer's setup function?? class myLayer(caffe.Layer): def setup(self, bottom, top): # I want to know here

问题 I'm trying to load in TEST phase a network configuration which has a memory data layer first and then a convolution layer. The MemoryData layer creation succeeds, But the convolution layer's creation fails at the following location: LOG(INFO) << "Creating layer " << param.name(); const string& type = param.type(); CreatorRegistry& registry = Registry(); CHECK_EQ(registry.count(type), 1) << "Unknown layer type: " << type << " (known types: " << LayerTypeList() << ")"; Printed error is: F0519

问题 I have a dataset of images that have multiple labels; There are 100 classes in the dataset, and each image has 1 to 5 labels associated with them. I'm following the instruction in the following URL: https://github.com/BVLC/caffe/issues/550 It says that I need to generate a text file listing the images and its labels as in /home/my_test_dir/picture-foo.jpg 0 /home/my_test_dir/picture-foo1.jpg 1 In my case, since I have multi-label images, does it work to simply add labels as in following?

问题 I thought we might be able to compile a Caffeinated description of some methods of performing multiple category classification . By multi category classification I mean: The input data containing representations of multiple model output categories and/or simply being classifiable under multiple model output categories. E.g. An image containing a cat & dog would output (ideally) ~1 for both the cat & dog prediction categories and ~0 for all others. Based on this paper, this stale and closed PR

问题 I want to design a convolutional neural network which occupy GPU resource no more than Alexnet.I want to use FLOPs to measure it but I don't know how to calculate it.Is there any tools to do it,please? 回答1: For online tool see http://dgschwend.github.io/netscope/#/editor . For alexnet see http://dgschwend.github.io/netscope/#/preset/alexnet . This supports most wide known layers. For custom layers you will have to calculate yourself. 回答2: For future visitors, if you use Keras and TensorFlow

问题 On Caffe, I am trying to implement a Fully Convolution Network for semantic segmentation. I was wondering is there a specific strategy to set up your 'solver.prototxt' values for the following hyper-parameters: test_iter test_interval iter_size max_iter Does it depend on the number of images you have for your training set? If so, how? 回答1: In order to set these values in a meaningful manner, you need to have a few more bits of information regarding your data: 1. Training set size the total

问题 (An update to this question has been added.) I am a graduate student at the university of Ghent, Belgium; my research is about emotion recognition with deep convolutional neural networks. I'm using the Caffe framework to implement the CNNs. Recently I've run into a problem concerning class imbalance. I'm using 9216 training samples, approx. 5% are labeled positively (1), the remaining samples are labeled negatively (0). I'm using the SigmoidCrossEntropyLoss layer to calculate the loss. When

问题 OS: ubuntu 16.04 CUDA: 7.5 Cudnn: 5 I am following this tutorial for installing caffe with gpu. In here, I wanted an installation of opencv 3.1. But the compilation of opencv is giving error when CUDA is already installed in the system. The error I get on trying to make opencv 3.1 is : /usr/include/string.h: In function ‘void* __mempcpy_inline(void*, const void*, size_t)’: /usr/include/string.h:652:42: error: ‘memcpy’ was not declared in this scope return (char *) memcpy (__dest, __src, __n)