使用py-faster-rcnn訓練VOC2007數據集時遇到問題

 

 

 

 

使用py-faster-rcnn訓練VOC2007數據集時遇到如下問題：

1. KeyError: 'chair'

File "/home/sai/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 217, in _load_pascal_annotation
cls = self._class_to_ind[obj.find('name').text.lower().strip()]
KeyError: 'chair'

解決：

You probably need to write some line of codes to ignore any objects with classes except the classes you are looking for when you are loading the annotation _load_pascal_annotation.
Something like
cls_objs = [
obj for obj, clas in objs, self._classes if obj.find('name').text== clas]

when you are loading the annotation in _load_pascal_annotation method, look for something like
objs = diff_objs (or non_diff_objs)
After that line insert something similar to below code

cls_objs = [obj for obj in objs if obj.find('name').text in self._classes]
objs = cls_objs


https://github.com/rbgirshick/py-faster-rcnn/issues/316

2. Check failed: error == cudaSuccess (30 vs. 0) unknown error

1. I'd just like to point out that CUDA runtime error (30) might show if your program is unable to create or open the /dev/nvidia-uvm device file. This is usually fixed by installing package nvidia-modprobe:

sudo apt-get install nvidia-modprobe

  Note also that since your GPU has compute capability 2.1 as per this page you will not be able to use CuDNN and will need to disable support for CuDNN in the Caffe makefile.

 2. The problem happened because modprobe could not insert nvidia_340_uvm.

Thus, I had to install nvidia_340_uvm via: sudo apt-get install nvidia-340-uvm.
對於第二點，由於我不是340的顯卡驅動，我運行后系統崩了。據說將其改為自己的驅動版本即可，我是378版本的驅動，將340換成378后顯示無法定位軟件包。

3. 我發現自己沒有裝cuda samples，參考別人的教程進行安裝。（系統和應用版本不一致，需注意）

編譯CUDA Samples

命令：

cd /usr/local/cuda-6.5/samples
sudo make

編譯完成后，進入路徑：/samples/bin/x86_64/linux/release

運行命令：

./deviceQuery

輸出：

./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "Tesla K40c"
  CUDA Driver Version / Runtime Version          6.5 / 6.5
  CUDA Capability Major/Minor version number:    3.5
  Total amount of global memory:                 11520 MBytes (12079136768 bytes)
  (15) Multiprocessors, (192) CUDA Cores/MP:     2880 CUDA Cores
  GPU Clock rate:                                745 MHz (0.75 GHz)
  Memory Clock rate:                             3004 Mhz
  Memory Bus Width:                              384-bit
  L2 Cache Size:                                 1572864 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 2 copy engine(s)
  Run time limit on kernels:                     No
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Enabled
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Bus ID / PCI location ID:           1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 6.5, CUDA Runtime Version = 6.5, NumDevs = 1, Device0 = Tesla K40c
Result = PASS

如果輸出上述信息，恭喜你，NVIDIA和CUDA安裝成功，則可以繼續進行下一步安裝Caffe環境。

（2.2.4.9）驗證NVIDIA 驅動和CUDA是否安裝成功

查看安裝NVIDIA驅動版本 命令：

cat /proc/driver/nvidia/version 

輸出

NVRM version: NVIDIA UNIX x86_64 Kernel Module  340.96  Sun Nov  8 22:33:28 PST 2015
GCC version:  gcc version 4.7.3 (Ubuntu/Linaro 4.7.3-12ubuntu1)
如果在最后出現 KeyError: 'xxxxxxxxxx'，請刪除 $FRCN_ROOT/data/VOCdevkit2007/annotations_cache/annots.pkl
如果中途發現標錯了數據，重新標注數據后，請刪除 $FRCN_ROOT/data/cache/voc_2007_trainval_gt_roidb.pkl
如果最后測試出現IndexError: too many indices for array，那是因為你的測試數據中缺少了某些類別。請根據錯誤提示，找到對應的代碼（$FRCN_ROOT/lib/datasets/voc_eval.py第148行），前面加上一個if語句：if len(BB) != 0:BB = BB[sorted_ind, :]