Issues filed for BVLC/caffe

View Full Project
Do you use caffe? Leave a review!

Rate of open issues in the last 60 days

caffe open issues (View Closed Issues)
  • almost 3 years I set the channel in deploy.txt =1 because my images are grayscal images. I need to add is_color=false in data_image_param. First of all in the Alexnet train_val.prototxt there is data_param and not data_image_param!!!! and when I add is_color in data_param I get this error "caffe.DataParameter" has no field named "is_color". Can you please help me?
  • almost 3 years I have two identical GPUs in my machine but when fine tune it seems only one of them is used #3
  • almost 3 years make grayscale lmdb problem
  • almost 3 years CUDNN doesn't support the dilated convolution at Lyaer ***
  • almost 3 years matcaffe compilation error- No such "header" file or directory
  • almost 3 years make: *** [.build_release/cuda/src/caffe/layers/detection_output_layer.o] Error 1
  • almost 3 years Ubuntu 16.04 β€œ/usr/bin/ld: cannot find -llmdb” error in Caffe compilation
  • almost 3 years libstdc++.so.6: version `GLIBCXX_3.4.21' not found
  • almost 3 years Zero accuracy, loss not decreasing and layers have the same value for different inputs
  • almost 3 years Issues with compiling caffe with python, undefined reference to `std::__cxx11::…'
  • almost 3 years error while loading shared libraries: libcaffe.so.1.0.0-rc3
  • almost 3 years bug report: floating point exception when stepsize 0
  • almost 3 years CUDA error after input layer reshape
  • almost 3 years Training weight dump out
  • almost 3 years problem.. /usr/bin/ld: cannot find -lopencv_imgcodecs
  • almost 3 years Caffe Regression: net prediction is much larger than label but the training loss is very small
  • almost 3 years Installing Caffe Windows
  • almost 3 years I couldn't import _caffe, while I could import caffe. With the help of cmake, I couldn't found _caffe.py.
  • almost 3 years .so of caffe which wrapper by myself run very slowly in cgo of golang and thrift(muiti threads)?
  • almost 3 years Caffe-opencl for Windows
  • almost 3 years Fine-Tuning 2 Fully Connected Layers (Classification and Regression)
  • almost 3 years Mac 10.12.1 Sierra Xcode 8.1 cmake 1.vecLib 2.numpy 3.anaconda opencv
  • almost 3 years How to modify the model to fit in your demand?
  • almost 3 years I'm new here, thanks for your help!
  • almost 3 years I met a trouble while trying to "import caffe"
  • almost 3 years Caffe Build Error
  • almost 3 years dlopen _caffe.so Symbol not found
  • almost 3 years test_gradient_based_solver.testbin gives memory corruption
  • almost 3 years Memory leaking ?
  • almost 3 years Loss Layer Should Die Loudly for Unsupported Arguments
  • almost 3 years compared with caffe engine, can cudnn save gpu memory?
  • almost 3 years Exception: β€œdot” not found in path in python on mac
  • almost 3 years Memory leak when using reshape
  • almost 3 years unresolved void __cdecl caffe::caffe_gpu_dot on windows7 64bit
  • almost 3 years [libprotobuf ERROR google/protobuf/descriptor_database.cc.57] , if when I import caffe with openCV
  • almost 3 years 'module' object has no attribute 'io', while importing caffe in Ubuntu 16.04
  • almost 3 years Caffe stuck waiting on multiple boost::condition_variable in all threads in caffe::BlockingQueue
  • almost 3 years How to make with cuDNN?
  • almost 3 years Something wrong with `make runtest`
  • almost 3 years Multi-GPU caffe trainning is slow with CuDNN
  • almost 3 years Caffe installation error on Mac
  • almost 3 years AttributeError: 'module' object has no attribute 'io'; a = caffe.io.caffe_pb2.BlobProto.FromString(proto_data)
  • almost 3 years CUDA invalid device ordinal
  • almost 3 years make pycaffe error1
  • almost 3 years How to perform finetuning on a network which has batch normalization layer?
  • almost 3 years Why different versions of caffe output very different results?
  • almost 3 years Add MATLAB support with the CMake build on windows
  • almost 3 years Please move calls to ShareData() to Reshape() function
  • almost 3 years Achieve more pooling type
  • almost 3 years Modifying padded values for convolution layer
  • almost 3 years caffe installation error with protobuf
  • almost 3 years Convolution padding check
  • almost 3 years Is it symbolic link about libcudart.so.5.5 or then cuda version problem?
  • almost 3 years Python function problem: no error information provides when prototxt parses error.
  • almost 3 years To save GPU memory by re-using.
  • almost 3 years How to check the layer type in Caffe source code
  • almost 3 years How to resize mean_file instead of resizing my lmdb?
  • almost 3 years Fast R-CNN for caffe-opencl
  • almost 3 years Mac OS Sierra Version 10.12 throws error while building latest commit of caffe
  • almost 3 years DeepFool implementation on Caffe
  • almost 3 years No support for unicode literals on caffe.Net
  • almost 3 years Computational error with K40
  • almost 3 years Mac import caffe error
  • almost 3 years Segmentation fault while running under .py file.
  • almost 3 years make runtest errro:
  • almost 3 years NVIDIA Jetson TX1 memory problem
  • almost 3 years AttributeError: 'module' object has no attribute 'io'
  • almost 3 years compile error in CPU only mode
  • almost 3 years How to feed the weights of the neurons in C++ to blobs in caffe?
  • almost 3 years can pycaffe pass gradient test?
  • almost 3 years protoc compiler not found
  • almost 3 years "dyld: lazy symbol binding failed" when i ran make runtest on Mac OS 10.9.3
  • almost 3 years Network with 2 images input.
  • almost 3 years Is there a relation between the number of iterations needed and the amount of training data provide ?
  • almost 3 years How to online fine-tune a model?
  • almost 3 years Solve the problem: "cannot find -lboost_python3" when using Python3 Ubuntu16.04
  • almost 3 years make matcaffe places library outside of build dir
  • almost 3 years To Brodyh
  • almost 3 years Undefined variable or function 'caffe'
  • almost 3 years runtest accuracy/roundoff failures in 26 CPUDevice tests when using MKL (all GPUDevice tests ok)
  • almost 3 years Should there be a Reshape function for contrastive_loss_layer
  • almost 3 years Running Caffe on Titan x Pascal - Windows
  • almost 3 years Question about learn rate in lenet net.
  • almost 3 years gpu docker buildfile tell download mismatch when RUN step3 sometimes
  • almost 3 years I can't find caffe.proto file in …\src\caffe\proto
  • almost 3 years how to regression in caffe
  • almost 3 years TimerTest Fails for GPUDevice on Windows
  • almost 3 years multi_label_image_data_layer
  • almost 3 years Installing caffe on ubuntu 16.04 with 2 versions of Cuda installed (7.5 and 8)
  • almost 3 years C++ Classifier on FromProto function
  • almost 3 years Compile with Matlab interface error
  • almost 3 years Inconsistent loss in shallow networks with MemoryData as input layer
  • almost 3 years Compile Termination Issue
  • almost 3 years convert imageset doesn't work for validation data of imagenet
  • almost 3 years Problem with the CPU_ONLY in the source code of caffe.cpp
  • almost 3 years Does anyone compile on ubuntu and have to change the #include location of hdf5.h?
  • almost 3 years infogain_loss_layer for 2D output
  • almost 3 years Docker error:Error: image library/caffe:cpu not found.
  • almost 3 years Cmake and make libgflags error
  • almost 3 years Caffe installation with Anaconda Python: libglogs libgflags error

caffe closed issues

  • almost 3 years Segmentation fault (core dumped) after add a new python layer
  • almost 3 years Errors when run the example of "Fine-tuning CaffeNet"
  • almost 3 years matcaffe compilation error- unrecognized command line option "-std=c++11"
  • almost 3 years Understanding the deconvolution in FCN-32.
  • almost 3 years make test fails in opencl branch: Error when compiling test_libdnn_pool.cpp
  • almost 3 years libcudart.so.8.0: cannot open shared object file: No such file or directory
  • almost 3 years File for {} is missing. Should be at: {}".format(key, val))
  • almost 3 years Cmake can't find boost
  • almost 3 years error when installing caffe
  • almost 3 years Typo in include/caffe/layers/accuracy_layer.hpp
  • almost 3 years Caffe installation issue with 'libculibos'.
  • almost 3 years Unknown CMake command "caffe_protobuf_generate_cpp_py"
  • almost 3 years Something wrong with GPU TITAN X (Pascal) ?
  • almost 3 years Using Matcaffe, Solver scaffolding done then matlab crashed.
  • almost 3 years blobs_lr vs lr_mult in caffe?
  • almost 3 years Check failed: data_
  • almost 3 years Request implement the Lp-pooling and Mixed pooling
  • almost 3 years How to performing Finetune on a network which has batch normalization layer?
  • almost 3 years During test phase, the output of Batch Normalization layer is not equal to (input-mean)/sqrt(var + eps)?
  • almost 3 years How to modify a prototxt programmatically?
  • almost 3 years ImportError when implementing Python Layer in Caffe
  • almost 3 years Where is Model ZOO wiki page?
  • almost 3 years Error with OpenCV imgcodecs while running make all
  • almost 3 years model zoo gone?
  • almost 3 years multi gpu support for lstm layer
  • almost 3 years Is there layers for feature(vector) indexing in caffe?
  • almost 3 years Purpose of set -e and $@ in train_quick.sh in cifar10 example
  • almost 3 years fatal error: hdf5.h: No such file or directory
  • almost 3 years Error when using β€œfcn.berkeleyvision.org”
  • almost 3 years The speed of detection slows down when the batch size is increased. Is it normal?
  • almost 3 years Check failed too many resources requested for launch for pooling_layer.cu
  • almost 3 years 123
  • almost 3 years Python kernel is dead when I switch to GPU mode and run net.forward()
  • almost 3 years question about deploy.prototxt
  • almost 3 years Caffe on Windows maintained?
  • almost 3 years Not able to download pretrianed caffe model files - Error: No route to host
  • almost 3 years Not able to download pretrianed caffe model files (.caffemodelfailed) - Error: No route to host
  • almost 3 years Feature extracted with caffe and caffe_windows seems different
  • almost 3 years Question about the binary protocal buffer
  • almost 3 years problem to compile caffe with cmake
  • over 2 years caffe cuda 8.0 fmake runtest failing
  • over 2 years Getting an error while using convert_imageset
  • over 2 years SoftmaxWithLoss layer for image segmentation
  • over 2 years set different learning rate for different loss task
  • over 2 years Web Demo Installation link broken
  • over 2 years Error in LeNet on MNIST example
  • over 2 years [doc] problematic markdown rendering at http://caffe.berkeleyvision.org/install_apt_debian.html
  • over 2 years status ==CURAND_STATUS_SUCCESS (201 vs. 0) CURAND_STATUS_LAUNCH_FAILURE
  • over 2 years Why there is no libcaffe.lib in windows branch installation.
  • over 2 years How to set "WITH_PYTHON_LAYER := 1"?
  • over 2 years comment