Question

我试图在SegNet上训练我自己的数据集（使用caffe），我准备了与segnet tutorial相同的数据集。当我尝试运行火车时，它向我显示了这个错误：

I0915 08:33:50.851986 49060 net.cpp:482] Collecting Learning Rate and Weight Decay.
I0915 08:33:50.852017 49060 net.cpp:247] Network initialization done.
I0915 08:33:50.852030 49060 net.cpp:248] Memory required for data: 1064448016
I0915 08:33:50.852730 49060 solver.cpp:42] Solver scaffolding done.
I0915 08:33:50.853065 49060 solver.cpp:250] Solving VGG_ILSVRC_16_layer
I0915 08:33:50.853080 49060 solver.cpp:251] Learning Rate Policy: step
F0915 08:33:51.324506 49060 math_functions.cu:123] Check failed: status == CUBLAS_STATUS_SUCCESS (11 vs. 0)  CUBLAS_STATUS_MAPPING_ERROR
*** Check failure stack trace: ***
    @     0x7fa27a0d3daa  (unknown)
    @     0x7fa27a0d3ce4  (unknown)
    @     0x7fa27a0d36e6  (unknown)
    @     0x7fa27a0d6687  (unknown)
    @     0x7fa27a56946e  caffe::caffe_gpu_asum<>()
    @     0x7fa27a54b264  caffe::SoftmaxWithLossLayer<>::Forward_gpu()
    @     0x7fa27a440b29  caffe::Net<>::ForwardFromTo()
    @     0x7fa27a440f57  caffe::Net<>::ForwardPrefilled()
    @     0x7fa27a436745  caffe::Solver<>::Step()
    @     0x7fa27a43707f  caffe::Solver<>::Solve()
    @           0x406676  train()
    @           0x404bb1  main
    @     0x7fa2795e5f45  (unknown)
    @           0x40515d  (unknown)
    @              (nil)  (unknown)

我的数据集是.jpg（火车）.png（标记灰度图像）和.txt文件，如教程中所示。可能是什么问题？谢谢你的帮助

Answer 1

地面实况图像应该是没有alpha层的1通道0-255图像，因此NN将识别类之间的差异。

img = Image.open(filename).convert('L') # Not 'LA' (A - alpha)

Answer 2

感谢isn4，以下是解决方案：事实证明，您必须更改像素值的范围以及实际的像素值数。如果您有256个可能的像素值（0-255）并且不为每个像素值设置类权重，Segnet会感到困惑。因此，我将所有PNG标签图像从255和0更改为像素可能性为1和0作为像素可能性。这是我的python脚本：

import os
import cv2
import numpy as np
img = cv2.imread('/usr/local/project/old_png_labels/label.png, 0)
a_img = np.array(img, np.double)
normalized = cv2.normalize(img, a_img, 1.0, 0.0, cv2.NORM_MINMAX)
cv2.imwrite('/usr/local//project/png_labels/label.png, normalized)

SegNet - CUBLAS_STATUS_SUCCESS（11对0）CUBLAS_STATUS_MAPPING_ERROR

2 个答案: