SRN_multilabel
No description available.
파일 탐색기
최종 버전 다운로드 (.zip)- demo.m
- flow_mean.mat
- rgb_mean.mat
- VideoSpatialPrediction.m
- VideoTemporalPrediction.m
- demo.py
- VideoSpatialPrediction.py
- VideoTemporalPrediction.py
- gflags.cmake
- glog.cmake
- FindAtlas.cmake
- FindGFlags.cmake
- FindGlog.cmake
- FindLAPACK.cmake
- FindLevelDB.cmake
- FindLMDB.cmake
- FindMatlabMex.cmake
- FindMKL.cmake
- FindNumPy.cmake
- FindOpenBLAS.cmake
- FindSnappy.cmake
- FindvecLib.cmake
- caffe_config.h.in
- CaffeConfig.cmake.in
- CaffeConfigVersion.cmake.in
- ConfigGen.cmake
- Cuda.cmake
- Dependencies.cmake
- lint.cmake
- Misc.cmake
- ProtoBuf.cmake
- Summary.cmake
- Targets.cmake
- Utils.cmake
- default.html
- caffeine-icon.png
- GitHub-Mark-64px.png
- pygment_trac.css
- reset.css
- styles.css
- .gitignore
- backward.jpg
- forward.jpg
- forward_backward.png
- layer.jpg
- logreg.jpg
- convolution.md
- data.md
- forward_backward.md
- index.md
- interfaces.md
- layers.md
- loss.md
- net_layer_blob.md
- solver.md
- _config.yml
- CMakeLists.txt
- CNAME
- development.md
- index.md
- install_apt.md
- install_osx.md
- install_yum.md
- installation.md
- model_zoo.md
- performance_hardware.md
- README.md
- train_flow_split1.txt
- train_rgb_split1.txt
- val_flow_split1.txt
- val_rgb_split1.txt
- train_action_recognition_flow.sh
- train_action_recognition_rgb.sh
- cifar10_full.prototxt
- cifar10_full_solver.prototxt
- cifar10_full_solver_lr1.prototxt
- cifar10_full_solver_lr2.prototxt
- cifar10_full_train_test.prototxt
- cifar10_quick.prototxt
- cifar10_quick_solver.prototxt
- cifar10_quick_solver_lr1.prototxt
- cifar10_quick_train_test.prototxt
- convert_cifar_data.cpp
- create_cifar10.sh
- readme.md
- train_full.sh
- train_quick.sh
- classification.cpp
- readme.md
- imagenet_val.prototxt
- readme.md
- assemble_data.py
- flickr_style.csv.gz
- readme.md
- style_names.txt
- pascal_finetune_solver.prototxt
- pascal_finetune_trainval_test.prototxt
- nonlinear_auto_test.prototxt
- nonlinear_auto_train.prototxt
- nonlinear_solver.prototxt
- nonlinear_train_val.prototxt
- solver.prototxt
- train_val.prototxt
- create_imagenet.sh
- make_imagenet_mean.sh
- readme.md
- resume_training.sh
- train_caffenet.sh
- cat.jpg
- cat_gray.jpg
- fish-bike.jpg
- convert_mnist_data.cpp
- create_mnist.sh
- lenet.prototxt
- lenet_auto_solver.prototxt
- lenet_consolidated_solver.prototxt
- lenet_multistep_solver.prototxt
- lenet_parallel_solver.prototxt
- lenet_solver.prototxt
- lenet_stepearly_solver.prototxt
- lenet_train_test.prototxt
- mnist_autoencoder.prototxt
- mnist_autoencoder_solver.prototxt
- mnist_autoencoder_solver_adagrad.prototxt
- mnist_autoencoder_solver_nesterov.prototxt
- readme.md
- train_lenet.sh
- train_lenet_consolidated.sh
- train_lenet_parallel.sh
- train_mnist_autoencoder.sh
- train_mnist_autoencoder_adagrad.sh
- train_mnist_autoencoder_nesterov.sh
- bvlc_caffenet_full_conv.prototxt
- conv.prototxt
- pyloss.py
- caffenet.py
- linreg.prototxt
- convert_mnist_siamese_data.cpp
- create_mnist_siamese.sh
- mnist_siamese.ipynb
- mnist_siamese.prototxt
- mnist_siamese_solver.prototxt
- mnist_siamese_train_test.prototxt
- readme.md
- train_mnist_siamese.sh
- index.html
- app.py
- exifutil.py
- readme.md
- requirements.txt
- 00-classification.ipynb
- 01-learning-lenet.ipynb
- 02-brewing-logreg.ipynb
- 03-fine-tuning.ipynb
- CMakeLists.txt
- detection.ipynb
- net_surgery.ipynb
- test_caffe_main.hpp
- test_gradient_check_util.hpp
- benchmark.hpp
- channel.hpp
- cudnn.hpp
- db.hpp
- db_leveldb.hpp
- db_lmdb.hpp
- device_alternate.hpp
- im2col.hpp
- insert_splits.hpp
- io.hpp
- math_functions.hpp
- mkl_alternate.hpp
- mpi_functions.hpp
- rng.hpp
- upgrade_proto.hpp
- blob.hpp
- caffe.hpp
- common.hpp
- common_layers.hpp
- data_layers.hpp
- data_transformer.hpp
- filler.hpp
- internal_thread.hpp
- layer.hpp
- layer_factory.hpp
- loss_layers.hpp
- net.hpp
- neuron_layers.hpp
- python_layer.hpp
- solver.hpp
- syncedmem.hpp
- vision_layers.hpp
- test_net.m
- test_solver.m
- ilsvrc_2012_mean.mat
- caffe_.cpp
- CHECK.m
- CHECK_FILE_EXIST.m
- is_valid_handle.m
- Blob.m
- get_net.m
- get_solver.m
- io.m
- Layer.m
- Net.m
- reset_all.m
- run_tests.m
- set_device.m
- set_mode_cpu.m
- set_mode_gpu.m
- Solver.m
- classification_demo.m
- .gitignore
- demo.m
- store2hdf5.m
- CMakeLists.txt
- ilsvrc_2012_mean.npy
- test_net.py
- test_net_spec.py
- test_python_layer.py
- test_solver.py
- __init__.py
- _caffe.cpp
- classifier.py
- detector.py
- draw.py
- io.py
- net_spec.py
- pycaffe.py
- bn_convert_style.py
- classify.py
- CMakeLists.txt
- convert_to_fully_conv.py
- detect.py
- draw_net.py
- gen_bn_inference.py
- polyak_average.py
- requirements.txt
- travis_build_and_test.sh
- travis_install.sh
- travis_setup_makefile_config.sh
- build_docs.sh
- copy_notebook.py
- cpp_lint.py
- deploy_docs.sh
- download_model_binary.py
- download_model_from_gist.sh
- gather_examples.sh
- upload_model_to_gist.sh
- absval_layer.cpp
- absval_layer.cu
- accuracy_layer.cpp
- argmax_layer.cpp
- base_conv_layer.cpp
- base_data_layer.cpp
- base_data_layer.cu
- batch_reduction_layer.cpp
- batch_reduction_layer.cu
- bias_layer.cpp
- bias_layer.cu
- bn_layer.cpp
- bn_layer.cu
- bnll_layer.cpp
- bnll_layer.cu
- concat_layer.cpp
- concat_layer.cu
- contrastive_loss_layer.cpp
- contrastive_loss_layer.cu
- conv_layer.cpp
- conv_layer.cu
- cudnn_bn_layer.cpp
- cudnn_bn_layer.cu
- cudnn_conv_layer.cpp
- cudnn_conv_layer.cu
- cudnn_pooling_layer.cpp
- cudnn_pooling_layer.cu
- cudnn_relu_layer.cpp
- cudnn_relu_layer.cu
- cudnn_sigmoid_layer.cpp
- cudnn_sigmoid_layer.cu
- cudnn_softmax_layer.cpp
- cudnn_softmax_layer.cu
- cudnn_tanh_layer.cpp
- cudnn_tanh_layer.cu
- data_layer.cpp
- deconv_layer.cpp
- deconv_layer.cu
- dropout_layer.cpp
- dropout_layer.cu
- dummy_data_layer.cpp
- eltwise_layer.cpp
- eltwise_layer.cu
- euclidean_loss_layer.cpp
- euclidean_loss_layer.cu
- exp_layer.cpp
- exp_layer.cu
- filter_layer.cpp
- filter_layer.cu
- flatten_layer.cpp
- gather_layer.cpp
- gather_layer.cu
- hdf5_data_layer.cpp
- hdf5_data_layer.cu
- hdf5_output_layer.cpp
- hdf5_output_layer.cu
- hinge_loss_layer.cpp
- im2col_layer.cpp
- im2col_layer.cu
- image_data_layer.cpp
- infogain_loss_layer.cpp
- inner_product_layer.cpp
- inner_product_layer.cu
- log_layer.cpp
- log_layer.cu
- loss_layer.cpp
- lrn_layer.cpp
- lrn_layer.cu
- memory_data_layer.cpp
- multinomial_logistic_loss_layer.cpp
- mvn_layer.cpp
- mvn_layer.cu
- neuron_layer.cpp
- normalize_layer.cpp
- normalize_layer.cu
- pooling_layer.cpp
- pooling_layer.cu
- power_layer.cpp
- power_layer.cu
- prelu_layer.cpp
- prelu_layer.cu
- reduction_layer.cpp
- reduction_layer.cu
- relu_layer.cpp
- relu_layer.cu
- reshape_layer.cpp
- roi_pooling_layer.cpp
- roi_pooling_layer.cu
- scale_layer.cpp
- scale_layer.cu
- scatter_layer.cpp
- scatter_layer.cu
- sigmoid_cross_entropy_loss_layer.cpp
- sigmoid_cross_entropy_loss_layer.cu
- sigmoid_layer.cpp
- sigmoid_layer.cu
- silence_layer.cpp
- silence_layer.cu
- slice_layer.cpp
- slice_layer.cu
- smooth_L1_loss_layer.cpp
- smooth_L1_loss_layer.cu
- softmax_layer.cpp
- softmax_layer.cu
- softmax_loss_layer.cpp
- softmax_loss_layer.cu
- split_layer.cpp
- split_layer.cu
- spp_layer.cpp
- tanh_layer.cpp
- tanh_layer.cu
- threshold_layer.cpp
- threshold_layer.cu
- tile_layer.cpp
- tile_layer.cu
- video_data_layer.cpp
- window_data_layer.cpp
- caffe.proto
- generate_sample_data.py
- sample_data.h5
- sample_data_2_gzip.h5
- sample_data_list.txt
- CMakeLists.txt
- test_accuracy_layer.cpp
- test_argmax_layer.cpp
- test_benchmark.cpp
- test_blob.cpp
- test_bn_layer.cpp
- test_caffe_main.cpp
- test_common.cpp
- test_concat_layer.cpp
- test_contrastive_loss_layer.cpp
- test_convolution_layer.cpp
- test_data_layer.cpp
- test_data_transformer.cpp
- test_db.cpp
- test_deconvolution_layer.cpp
- test_dummy_data_layer.cpp
- test_eltwise_layer.cpp
- test_euclidean_loss_layer.cpp
- test_filler.cpp
- test_filter_layer.cpp
- test_flatten_layer.cpp
- test_gradient_based_solver.cpp
- test_hdf5_output_layer.cpp
- test_hdf5data_layer.cpp
- test_hinge_loss_layer.cpp
- test_im2col_kernel.cu
- test_im2col_layer.cpp
- test_image_data_layer.cpp
- test_infogain_loss_layer.cpp
- test_inner_product_layer.cpp
- test_internal_thread.cpp
- test_io.cpp
- test_layer_factory.cpp
- test_lrn_layer.cpp
- test_math_functions.cpp
- test_maxpool_dropout_layers.cpp
- test_memory_data_layer.cpp
- test_multinomial_logistic_loss_layer.cpp
- test_mvn_layer.cpp
- test_net.cpp
- test_neuron_layer.cpp
- test_platform.cpp
- test_pooling_layer.cpp
- test_power_layer.cpp
- test_protobuf.cpp
- test_random_number_generator.cpp
- test_reduction_layer.cpp
- test_reshape_layer.cpp
- test_roi_pooling_layer.cpp
- test_scale_layer.cpp
- test_sigmoid_cross_entropy_loss_layer.cpp
- test_slice_layer.cpp
- test_softmax_layer.cpp
- test_softmax_with_loss_layer.cpp
- test_solver.cpp
- test_split_layer.cpp
- test_spp_layer.cpp
- test_stochastic_pooling.cpp
- test_syncedmem.cpp
- test_tanh_layer.cpp
- test_threshold_layer.cpp
- test_upgrade_proto.cpp
- test_util_blas.cpp
- benchmark.cpp
- channel.cpp
- cudnn.cpp
- db.cpp
- db_leveldb.cpp
- db_lmdb.cpp
- im2col.cpp
- im2col.cu
- insert_splits.cpp
- io.cpp
- math_functions.cpp
- math_functions.cu
- mpi_functions.cpp
- upgrade_proto.cpp
- blob.cpp
- CMakeLists.txt
- common.cpp
- data_transformer.cpp
- internal_thread.cpp
- layer_factory.cpp
- net.cpp
- solver.cpp
- syncedmem.cpp
- CMakeLists.txt
- gtest-all.cpp
- gtest.h
- gtest_main.cc
- extract_seconds.py
- launch_resize_and_crop_images.sh
- parse_log.py
- parse_log.sh
- plot_log.gnuplot.example
- plot_training_log.py.example
- resize_and_crop_images.py
- caffe.cpp
- CMakeLists.txt
- compute_image_mean.cpp
- convert_imageset.cpp
- device_query.cpp
- extract_features.cpp
- finetune_net.cpp
- net_speed_benchmark.cpp
- test_net.cpp
- train_net.cpp
- upgrade_net_proto_binary.cpp
- upgrade_net_proto_text.cpp
- .Doxyfile
- .gitignore
- .travis.yml
- caffe.cloc
- CHANGELOG.md
- CMakeLists.txt
- CONTRIBUTORS.md
- INSTALL.md
- LICENSE
- MAKE.sh
- MAKE_with_cudnn.sh
- Makefile
- Makefile.config.example
- README.md
- AP_VOC.m
- create_label_lmdb.py
- get_mAP_eccv16.m
- model_test.py
- precision_recall_f1.m
- srn_io.py
- evaluate.m
- README.md
- run_test.sh
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/zhufengx/SRN_multilabel
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd SRN_multilabel
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. CMake
보통 추천사전 준비물
cd caffe
이 프로젝트의 관련 파일이 하위 폴더 안에 있어서, 먼저 그 폴더로 이동합니다.
mkdir build && cd build
빌드 결과물을 담을 폴더를 만들고 그 안으로 이동합니다.
cmake ..
소스코드를 분석해 빌드 설정 파일을 생성합니다 (build 폴더 안에서 실행해야 함).
make
생성된 빌드 설정을 바탕으로 실제 컴파일을 진행해 실행 파일을 만듭니다.
build 폴더 안에 실행 파일이 생성됐는지 확인하고, 직접 실행해보세요 (예: ./build/앱이름).
3. Python
쉬움사전 준비물
⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.
pip install -r caffe/python/requirements.txt
requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.
jupyter notebook
브라우저에서 노트북(.ipynb) 파일들을 열람하고 실행할 수 있는 Jupyter 화면을 켭니다.
에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.
4. Make
보통사전 준비물
- Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
- Make Linux/macOS는 보통 기본 설치되어 있습니다. Windows는 별도 설치(예: MSYS2, WSL)가 필요합니다.
cd caffe
이 프로젝트의 관련 파일이 하위 폴더 안에 있어서, 먼저 그 폴더로 이동합니다.
make
생성된 빌드 설정을 바탕으로 실제 컴파일을 진행해 실행 파일을 만듭니다.
에러 없이 끝나면 성공입니다. 생성된 실행 파일을 직접 실행해보세요.
// repository documentation
Was this content helpful?
(0 ratings)