Cannot run R-CNN example

[kar-fai]

Hi, I am using the docker from tleyden5iwx/caffe-gpu-master

However, I get the error when I run the R-CNN examples by typing this command.

python python/detect.py \
--crop_mode=selective_search \
--pretrained_model=/opt/caffe/models/bvlc_reference_rcnn_ilsvrc13/bvlc_reference_rcnn_ilsvrc13.caffemodel \
--model_def=/opt/caffe/models/bvlc_reference_rcnn_ilsvrc13/deploy.prototxt \
--gpu \
--raw_scale=255 \
_temp/det_input.txt _temp/det_output.h5

This is the output from terminal

libdc1394 error: Failed to initialize libdc1394
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0607 08:48:22.059032 24964 net.cpp:42] Initializing net from parameters: 
name: "R-CNN-ilsvrc13"
input: "data"
input_dim: 10
input_dim: 3
input_dim: 227
input_dim: 227
state {
  phase: TEST
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "conv1"
  top: "conv1"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm1"
  type: "LRN"
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "norm1"
  top: "conv2"
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "norm2"
  type: "LRN"
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "norm2"
  top: "conv3"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "conv4"
  type: "Convolution"
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
  }
}
layer {
  name: "relu4"
  type: "ReLU"
  bottom: "conv4"
  top: "conv4"
}
layer {
  name: "conv5"
  type: "Convolution"
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
  }
}
layer {
  name: "relu5"
  type: "ReLU"
  bottom: "conv5"
  top: "conv5"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc-rcnn"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc-rcnn"
  inner_product_param {
    num_output: 200
  }
}
I0607 08:48:22.059561 24964 net.cpp:336] Input 0 -> data
I0607 08:48:22.059597 24964 layer_factory.hpp:74] Creating layer conv1
I0607 08:48:22.059607 24964 net.cpp:76] Creating Layer conv1
I0607 08:48:22.059615 24964 net.cpp:372] conv1 <- data
I0607 08:48:22.059625 24964 net.cpp:334] conv1 -> conv1
I0607 08:48:22.059634 24964 net.cpp:105] Setting up conv1
I0607 08:48:22.059712 24964 net.cpp:112] Top shape: 10 96 55 55 (2904000)
I0607 08:48:22.059737 24964 layer_factory.hpp:74] Creating layer relu1
I0607 08:48:22.059746 24964 net.cpp:76] Creating Layer relu1
I0607 08:48:22.059749 24964 net.cpp:372] relu1 <- conv1
I0607 08:48:22.059756 24964 net.cpp:323] relu1 -> conv1 (in-place)
I0607 08:48:22.059762 24964 net.cpp:105] Setting up relu1
I0607 08:48:22.059770 24964 net.cpp:112] Top shape: 10 96 55 55 (2904000)
I0607 08:48:22.059775 24964 layer_factory.hpp:74] Creating layer pool1
I0607 08:48:22.059782 24964 net.cpp:76] Creating Layer pool1
I0607 08:48:22.059787 24964 net.cpp:372] pool1 <- conv1
I0607 08:48:22.059792 24964 net.cpp:334] pool1 -> pool1
I0607 08:48:22.059798 24964 net.cpp:105] Setting up pool1
I0607 08:48:22.059806 24964 net.cpp:112] Top shape: 10 96 27 27 (699840)
I0607 08:48:22.059810 24964 layer_factory.hpp:74] Creating layer norm1
I0607 08:48:22.059818 24964 net.cpp:76] Creating Layer norm1
I0607 08:48:22.059823 24964 net.cpp:372] norm1 <- pool1
I0607 08:48:22.059828 24964 net.cpp:334] norm1 -> norm1
I0607 08:48:22.059834 24964 net.cpp:105] Setting up norm1
I0607 08:48:22.059841 24964 net.cpp:112] Top shape: 10 96 27 27 (699840)
I0607 08:48:22.059846 24964 layer_factory.hpp:74] Creating layer conv2
I0607 08:48:22.059851 24964 net.cpp:76] Creating Layer conv2
I0607 08:48:22.059855 24964 net.cpp:372] conv2 <- norm1
I0607 08:48:22.059861 24964 net.cpp:334] conv2 -> conv2
I0607 08:48:22.059867 24964 net.cpp:105] Setting up conv2
I0607 08:48:22.060230 24964 net.cpp:112] Top shape: 10 256 27 27 (1866240)
I0607 08:48:22.060250 24964 layer_factory.hpp:74] Creating layer relu2
I0607 08:48:22.060256 24964 net.cpp:76] Creating Layer relu2
I0607 08:48:22.060263 24964 net.cpp:372] relu2 <- conv2
I0607 08:48:22.060268 24964 net.cpp:323] relu2 -> conv2 (in-place)
I0607 08:48:22.060274 24964 net.cpp:105] Setting up relu2
I0607 08:48:22.060278 24964 net.cpp:112] Top shape: 10 256 27 27 (1866240)
I0607 08:48:22.060282 24964 layer_factory.hpp:74] Creating layer pool2
I0607 08:48:22.060287 24964 net.cpp:76] Creating Layer pool2
I0607 08:48:22.060292 24964 net.cpp:372] pool2 <- conv2
I0607 08:48:22.060297 24964 net.cpp:334] pool2 -> pool2
I0607 08:48:22.060302 24964 net.cpp:105] Setting up pool2
I0607 08:48:22.060307 24964 net.cpp:112] Top shape: 10 256 13 13 (432640)
I0607 08:48:22.060312 24964 layer_factory.hpp:74] Creating layer norm2
I0607 08:48:22.060317 24964 net.cpp:76] Creating Layer norm2
I0607 08:48:22.060322 24964 net.cpp:372] norm2 <- pool2
I0607 08:48:22.060328 24964 net.cpp:334] norm2 -> norm2
I0607 08:48:22.060334 24964 net.cpp:105] Setting up norm2
I0607 08:48:22.060340 24964 net.cpp:112] Top shape: 10 256 13 13 (432640)
I0607 08:48:22.060345 24964 layer_factory.hpp:74] Creating layer conv3
I0607 08:48:22.060353 24964 net.cpp:76] Creating Layer conv3
I0607 08:48:22.060361 24964 net.cpp:372] conv3 <- norm2
I0607 08:48:22.060366 24964 net.cpp:334] conv3 -> conv3
I0607 08:48:22.060371 24964 net.cpp:105] Setting up conv3
I0607 08:48:22.061478 24964 net.cpp:112] Top shape: 10 384 13 13 (648960)
I0607 08:48:22.061504 24964 layer_factory.hpp:74] Creating layer relu3
I0607 08:48:22.061511 24964 net.cpp:76] Creating Layer relu3
I0607 08:48:22.061518 24964 net.cpp:372] relu3 <- conv3
I0607 08:48:22.061527 24964 net.cpp:323] relu3 -> conv3 (in-place)
I0607 08:48:22.061532 24964 net.cpp:105] Setting up relu3
I0607 08:48:22.061537 24964 net.cpp:112] Top shape: 10 384 13 13 (648960)
I0607 08:48:22.061542 24964 layer_factory.hpp:74] Creating layer conv4
I0607 08:48:22.061547 24964 net.cpp:76] Creating Layer conv4
I0607 08:48:22.061550 24964 net.cpp:372] conv4 <- conv3
I0607 08:48:22.061555 24964 net.cpp:334] conv4 -> conv4
I0607 08:48:22.061561 24964 net.cpp:105] Setting up conv4
I0607 08:48:22.062374 24964 net.cpp:112] Top shape: 10 384 13 13 (648960)
I0607 08:48:22.062396 24964 layer_factory.hpp:74] Creating layer relu4
I0607 08:48:22.062402 24964 net.cpp:76] Creating Layer relu4
I0607 08:48:22.062407 24964 net.cpp:372] relu4 <- conv4
I0607 08:48:22.062414 24964 net.cpp:323] relu4 -> conv4 (in-place)
I0607 08:48:22.062419 24964 net.cpp:105] Setting up relu4
I0607 08:48:22.062423 24964 net.cpp:112] Top shape: 10 384 13 13 (648960)
I0607 08:48:22.062428 24964 layer_factory.hpp:74] Creating layer conv5
I0607 08:48:22.062434 24964 net.cpp:76] Creating Layer conv5
I0607 08:48:22.062438 24964 net.cpp:372] conv5 <- conv4
I0607 08:48:22.062444 24964 net.cpp:334] conv5 -> conv5
I0607 08:48:22.062450 24964 net.cpp:105] Setting up conv5
I0607 08:48:22.062999 24964 net.cpp:112] Top shape: 10 256 13 13 (432640)
I0607 08:48:22.063020 24964 layer_factory.hpp:74] Creating layer relu5
I0607 08:48:22.063026 24964 net.cpp:76] Creating Layer relu5
I0607 08:48:22.063032 24964 net.cpp:372] relu5 <- conv5
I0607 08:48:22.063040 24964 net.cpp:323] relu5 -> conv5 (in-place)
I0607 08:48:22.063045 24964 net.cpp:105] Setting up relu5
I0607 08:48:22.063050 24964 net.cpp:112] Top shape: 10 256 13 13 (432640)
I0607 08:48:22.063055 24964 layer_factory.hpp:74] Creating layer pool5
I0607 08:48:22.063060 24964 net.cpp:76] Creating Layer pool5
I0607 08:48:22.063065 24964 net.cpp:372] pool5 <- conv5
I0607 08:48:22.063069 24964 net.cpp:334] pool5 -> pool5
I0607 08:48:22.063076 24964 net.cpp:105] Setting up pool5
I0607 08:48:22.063081 24964 net.cpp:112] Top shape: 10 256 6 6 (92160)
I0607 08:48:22.063086 24964 layer_factory.hpp:74] Creating layer fc6
I0607 08:48:22.063094 24964 net.cpp:76] Creating Layer fc6
I0607 08:48:22.063101 24964 net.cpp:372] fc6 <- pool5
I0607 08:48:22.063109 24964 net.cpp:334] fc6 -> fc6
I0607 08:48:22.063117 24964 net.cpp:105] Setting up fc6
I0607 08:48:22.119091 24964 net.cpp:112] Top shape: 10 4096 1 1 (40960)
I0607 08:48:22.119133 24964 layer_factory.hpp:74] Creating layer relu6
I0607 08:48:22.119158 24964 net.cpp:76] Creating Layer relu6
I0607 08:48:22.119166 24964 net.cpp:372] relu6 <- fc6
I0607 08:48:22.119179 24964 net.cpp:323] relu6 -> fc6 (in-place)
I0607 08:48:22.119189 24964 net.cpp:105] Setting up relu6
I0607 08:48:22.119205 24964 net.cpp:112] Top shape: 10 4096 1 1 (40960)
I0607 08:48:22.119211 24964 layer_factory.hpp:74] Creating layer drop6
I0607 08:48:22.119223 24964 net.cpp:76] Creating Layer drop6
I0607 08:48:22.119240 24964 net.cpp:372] drop6 <- fc6
I0607 08:48:22.119247 24964 net.cpp:323] drop6 -> fc6 (in-place)
I0607 08:48:22.119256 24964 net.cpp:105] Setting up drop6
I0607 08:48:22.119262 24964 net.cpp:112] Top shape: 10 4096 1 1 (40960)
I0607 08:48:22.119267 24964 layer_factory.hpp:74] Creating layer fc7
I0607 08:48:22.119274 24964 net.cpp:76] Creating Layer fc7
I0607 08:48:22.119279 24964 net.cpp:372] fc7 <- fc6
I0607 08:48:22.119285 24964 net.cpp:334] fc7 -> fc7
I0607 08:48:22.119292 24964 net.cpp:105] Setting up fc7
I0607 08:48:22.143841 24964 net.cpp:112] Top shape: 10 4096 1 1 (40960)
I0607 08:48:22.143887 24964 layer_factory.hpp:74] Creating layer relu7
I0607 08:48:22.143901 24964 net.cpp:76] Creating Layer relu7
I0607 08:48:22.143911 24964 net.cpp:372] relu7 <- fc7
I0607 08:48:22.143921 24964 net.cpp:323] relu7 -> fc7 (in-place)
I0607 08:48:22.143931 24964 net.cpp:105] Setting up relu7
I0607 08:48:22.143936 24964 net.cpp:112] Top shape: 10 4096 1 1 (40960)
I0607 08:48:22.143941 24964 layer_factory.hpp:74] Creating layer drop7
I0607 08:48:22.143960 24964 net.cpp:76] Creating Layer drop7
I0607 08:48:22.143970 24964 net.cpp:372] drop7 <- fc7
I0607 08:48:22.143976 24964 net.cpp:323] drop7 -> fc7 (in-place)
I0607 08:48:22.143985 24964 net.cpp:105] Setting up drop7
I0607 08:48:22.143991 24964 net.cpp:112] Top shape: 10 4096 1 1 (40960)
I0607 08:48:22.143996 24964 layer_factory.hpp:74] Creating layer fc-rcnn
I0607 08:48:22.144003 24964 net.cpp:76] Creating Layer fc-rcnn
I0607 08:48:22.144007 24964 net.cpp:372] fc-rcnn <- fc7
I0607 08:48:22.144014 24964 net.cpp:334] fc-rcnn -> fc-rcnn
I0607 08:48:22.144024 24964 net.cpp:105] Setting up fc-rcnn
I0607 08:48:22.144906 24964 net.cpp:112] Top shape: 10 200 1 1 (2000)
I0607 08:48:22.144925 24964 net.cpp:165] fc-rcnn does not need backward computation.
I0607 08:48:22.144930 24964 net.cpp:165] drop7 does not need backward computation.
I0607 08:48:22.144934 24964 net.cpp:165] relu7 does not need backward computation.
I0607 08:48:22.144951 24964 net.cpp:165] fc7 does not need backward computation.
I0607 08:48:22.144958 24964 net.cpp:165] drop6 does not need backward computation.
I0607 08:48:22.144963 24964 net.cpp:165] relu6 does not need backward computation.
I0607 08:48:22.144968 24964 net.cpp:165] fc6 does not need backward computation.
I0607 08:48:22.144973 24964 net.cpp:165] pool5 does not need backward computation.
I0607 08:48:22.144978 24964 net.cpp:165] relu5 does not need backward computation.
I0607 08:48:22.144981 24964 net.cpp:165] conv5 does not need backward computation.
I0607 08:48:22.144985 24964 net.cpp:165] relu4 does not need backward computation.
I0607 08:48:22.144989 24964 net.cpp:165] conv4 does not need backward computation.
I0607 08:48:22.144994 24964 net.cpp:165] relu3 does not need backward computation.
I0607 08:48:22.144997 24964 net.cpp:165] conv3 does not need backward computation.
I0607 08:48:22.145001 24964 net.cpp:165] norm2 does not need backward computation.
I0607 08:48:22.145006 24964 net.cpp:165] pool2 does not need backward computation.
I0607 08:48:22.145012 24964 net.cpp:165] relu2 does not need backward computation.
I0607 08:48:22.145016 24964 net.cpp:165] conv2 does not need backward computation.
I0607 08:48:22.145021 24964 net.cpp:165] norm1 does not need backward computation.
I0607 08:48:22.145025 24964 net.cpp:165] pool1 does not need backward computation.
I0607 08:48:22.145030 24964 net.cpp:165] relu1 does not need backward computation.
I0607 08:48:22.145032 24964 net.cpp:165] conv1 does not need backward computation.
I0607 08:48:22.145037 24964 net.cpp:201] This network produces output fc-rcnn
I0607 08:48:22.145051 24964 net.cpp:446] Collecting Learning Rate and Weight Decay.
I0607 08:48:22.145059 24964 net.cpp:213] Network initialization done.
I0607 08:48:22.145063 24964 net.cpp:214] Memory required for data: 62425920
E0607 08:48:22.439707 24964 upgrade_proto.cpp:618] Attempting to upgrade input file specified using deprecated V1LayerParameter: /opt/caffe/models/bvlc_reference_rcnn_ilsvrc13/bvlc_reference_rcnn_ilsvrc13.caffemodel
I0607 08:48:22.615486 24964 upgrade_proto.cpp:626] Successfully upgraded file specified using deprecated V1LayerParameter
GPU mode
Loading input...
selective_search_rcnn({'/opt/caffe/images/fish-bike.jpg'}, '/tmp/tmpKULeLF.mat')

Traceback (most recent call last):
  File "python/detect.py", line 170, in <module>
    main(sys.argv)
  File "python/detect.py", line 141, in main
    detections = detector.detect_selective_search(inputs)
  File "/opt/caffe/python/caffe/detector.py", line 118, in detect_selective_search
    cmd='selective_search_rcnn'
  File "/opt/caffe/python/caffe/selective_search_ijcv_with_python/selective_search.py", line 36, in get_windows
    shlex.split(mc), stdout=open('/dev/null', 'w'), cwd=script_dirname)
  File "/usr/lib/python2.7/subprocess.py", line 710, in __init__
    errread, errwrite)
  File "/usr/lib/python2.7/subprocess.py", line 1327, in _execute_child
    raise child_exception
OSError: [Errno 2] No such file or directory

My gpu installed Cuda-6.5 and Matlab R2014b without any issue.
I pass my nvidia devices and matlab application to docker by using this command in terminal

DOCKER_NVIDIA_DEVICES="--device /dev/nvidia0:/dev/nvidia0 --device /dev/nvidiactl:/dev/nvidiactl --device /dev/nvidia-uvm:/dev/nvidia-uvm"
sudo docker run -ti --rm $DOCKER_NVIDIA_DEVICES -v /usr/local/MATLAB:/usr/local/MATLAB tleyden5iwx/caffe-gpu-master /bin/bash

Below is my Makefile.config

## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
# USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1

# To customize your choice of compiler, uncomment and set the following.
# N.B. the default for Linux is g++ and the default for OSX is clang++
# CUSTOM_CXX := g++

# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda
# On Ubuntu 14.04, if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

# CUDA architecture setting: going with all of them.
# For CUDA < 6.0, comment the *_50 lines for compatibility.
CUDA_ARCH := -gencode arch=compute_20,code=sm_20 \
        -gencode arch=compute_20,code=sm_21 \
        -gencode arch=compute_30,code=sm_30 \
        -gencode arch=compute_35,code=sm_35 \
        -gencode arch=compute_50,code=sm_50 \
        -gencode arch=compute_50,code=compute_50

# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := atlas
# Custom (MKL/ATLAS/OpenBLAS) include and lib directories.
# Leave commented to accept the defaults for your choice of BLAS
# (which should work)!
# BLAS_INCLUDE := /path/to/your/blas
# BLAS_LIB := /path/to/your/blas

# This is required only if you will compile the matlab interface.
# MATLAB directory should contain the mex binary in /bin.
MATLAB_DIR := /usr/local/MATLAB/R2014b
# MATLAB_DIR := /Applications/MATLAB_R2012b.app

# NOTE: this is required only if you will compile the python interface.
# We need to be able to find Python.h and numpy/arrayobject.h.
PYTHON_INCLUDE := /usr/include/python2.7 \
        /usr/lib/python2.7/dist-packages/numpy/core/include
# Anaconda Python distribution is quite popular. Include path:
# Verify anaconda location, sometimes it's in root.
# ANACONDA_HOME := $(HOME)/anaconda
# PYTHON_INCLUDE := $(ANACONDA_HOME)/include \
        # $(ANACONDA_HOME)/include/python2.7 \
        # $(ANACONDA_HOME)/lib/python2.7/site-packages/numpy/core/include \

# We need to be able to find libpythonX.X.so or .dylib.
PYTHON_LIB := /usr/lib
# PYTHON_LIB := $(ANACONDA_HOME)/lib

# Uncomment to support layers written in Python (will link against Python libs)
# WITH_PYTHON_LAYER := 1

# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib

# Uncomment to use `pkg-config` to specify OpenCV library paths.
# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
# USE_PKG_CONFIG := 1

BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
# DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @
CXX := /usr/bin/g++-4.6

Next, go to the caffe root directory which is /opt/caffe, and type

make clean
make all -j8
make test -j8
make runtest -j8

This is the output of last few lines

[==========] 1026 tests from 190 test cases ran. (91992 ms total)
[  PASSED  ] 1026 tests.

  YOU HAVE 2 DISABLED TESTS

Compile the Python wrappers, by type make pycaffe, I get output below

CXX/LD -o python/caffe/_caffe.so python/caffe/_caffe.cpp
touch python/caffe/proto/__init__.py
PROTOC (python) src/caffe/proto/caffe.proto

Compile the Matlab wrappers, by type make matcaffe, I get output below

MEX matlab/caffe/matcaffe.cpp
Building with 'g++'.
MEX completed successfully.

In additional, I can run the LeNet MNIST tutorial and Imagenet classification examples without any issue, but not R-CNN. Help please?

[kar-fai]

Just found the solution on #1030. This is due to 'matlab' command is not available in terminal. To solve this, add

export PATH=/usr/local/MATLAB/R2014b/bin/:$PATH

with assumption that your MATLAB installed in directory /usr/local/

[SevenBlocks]

I had this same problem. Thanks for posting the solution.

[baolinhtb]

I also got the same problem, Thank you very much!! Kar-fai