caffe

问题 I want to use caffe with a vector label, not integer. I have checked some answers, and it seems HDF5 is a better way. But then I'm stucked with error like: accuracy_layer.cpp:34] Check failed: outer_num_ * inner_num_ == bottom[1]->count() (50 vs. 200) Number of labels must match number of predictions; e.g., if label axis == 1 and prediction shape is (N, C, H, W), label count (number of labels) must be N*H*W , with integer values in {0, 1, ..., C-1}. with HDF5 created as: f = h5py.File('train

问题 I want to use caffe with a vector label, not integer. I have checked some answers, and it seems HDF5 is a better way. But then I'm stucked with error like: accuracy_layer.cpp:34] Check failed: outer_num_ * inner_num_ == bottom[1]->count() (50 vs. 200) Number of labels must match number of predictions; e.g., if label axis == 1 and prediction shape is (N, C, H, W), label count (number of labels) must be N*H*W , with integer values in {0, 1, ..., C-1}. with HDF5 created as: f = h5py.File('train

问题 After install caffe in conda virtual environment with Python 3.5 I am getting this error on importing caffe Traceback (most recent call last): File "", line 1, in File "/var/caffe-master/python/caffe/ init .py", line 1, in from .pycaffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, RMSPropSolver, AdaDeltaSolver, AdamSolver, NCCL, Timer File "/var/caffe-master/python/caffe/pycaffe.py", line 13, in from ._caffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, \ ImportError: /usr

问题 I trained my data using Caffe. Below are the parameters in solver.prototxt file. test_iter: 100 test_interval: 1000 base_lr: 0.00001 lr_policy: "step" gamma: 0.1 stepsize: 20000 display: 20 max_iter: 13000 momentum: 0.9 weight_decay: 0.0005 snapshot: 10000 solver_mode: GPU The test accuracy is around 0.0185 and test loss is around 2.85 at the first test. At iter 13000 the test accuracy is .92 and the test loss is 0.52. How do I evaluate whether the accuracy is good or is it over fitting the

问题 What I want to do is to do a simple pixel-wise classification or regression task. Therefore I have an input image and a ground_truth. What I want to do is to do an easy segmentation task where I have a circle and a rectangle. And I want to train, where the circle or where the rectangle is. That means I have an ground_truth images which has value "1" at all the locations where the circle is and value "2" at all the locations where the rectangle is. Then I have my images and ground_truth images

问题 I want to include caffe in my project. This is the folder structure of the project: . ├── AUTHORS ├── ChangeLog ├── cmake │ ├── FindCaffe.cmake │ └── FindCUDA.cmake ├── CMakeLists.txt ├── CMakeLists.txt.user ├── data │ └── info.plist ├── deep-app.pro.user ├── LICENSE.txt ├── README.md ├── [reference] │ ├── deep-app.pro │ ├── deep-app.pro.user │ ├── deployment.pri │ ├── main.cpp │ ├── main.qml │ ├── Page1Form.ui.qml │ ├── Page1.qml │ └── qml.qrc └── src ├── CMakeLists.txt ├── code │ └── main

问题 I have two images/patches (the larger one includes the smaller one and some context information around it) of different sizes (I dont wont to create a new image by just concatenating them). I want to create a CNN as shown in the figure. How can I create it using Caffe prototxt file? Can I directly use Caffe to train it? Both CNNs can share the same weights. 来源： https://stackoverflow.com/questions/38226378/how-to-create-this-cnn-architecture-in-caffe

问题 Background: I wish to use both Caffe and Digits such that I can use Caffe within the Digits framework or external to it. However, for a particular project, I require that Caffe uses OpenCV 3 and not OpenCV 2.4, which Digits installs by default. This project uses Caffe external to Digits, and does not make any use of the Digits framework. It appears that by installing Digits, my OpenCV 3 installation was "clobbered" with OpenCV 2.4, which is now causing problems within my original Caffe

问题 I used Caffe GoogleNet model to train my own data (10k images, 2 classes). I stop it at 400000th iteration with an accuracy of ~80%. If I run the below command: ./build/examples/cpp_classification/classification.bin models/bvlc_googlenet/deploy.prototxt models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel data/ilsvrc12/imagenet_mean.binaryproto data/ilsvrc12/synset_words.txt 1.png it gives me a different -- apparently random -- result each time (i.e. if I run it n times, then I

问题 I have a really weird problem I want to explain to you. I am not sure if this is a topic for SO but I hope it will be in the end. My general problem task is depth estimation, i.e. I have an image as input and its corresponding ground_truth (depth image). Then I have my net (which should be considered as black box) and my last layers. First of all depth estimation is rather a regression task than a classification task. Therefore I decided to use a EuclideanLoss layer where my num_output of my