devbox
我家自动化
这个屌丝很懒，什么也没留下！
关注作者
热门标签
热门文章
当前位置:   article > 正文

遇到问题EGNet(1): 测试报错_non-broadcastable output operand with shape (1,) d

作者：我家自动化 | 2024-04-06 06:50:20

赞

踩

non-broadcastable output operand with shape (1,) doesn't match the broadcast

１　输入指令:（PS:模式test 显著性数据集是ECSSD）

python3 run.py --mode test --sal_mode e

２　模型&数据集放置如下:（PS:请问选中的这两个的放置位置是否正确？对的,另外这个ECSSD是自己下载的,里面内容改名如下）
　　

３　报错如下：（PS:报错核心部分，原因是图片没有读取到）

ValueError: non-broadcastable output operand with shape () doesn't match the broadcast shape (3,)
File Not Exists

４　备注：（PS:我把你的相对路径改成了相对路径，对应如下）
run.py

  1. if __name__ == '__main__':
  2.  
  3.     # vgg_path = '/home/liuj/code/Messal/weights/vgg16_20M.pth'
  4.     vgg_path = './weights/vgg16_20M.pth'
  5.     # vgg_path = '/home/liuj/code/Messal/weights/resnet50_caffe.pth'
  6.     resnet_path = './weights/resnet50_caffe.pth'

dataset.py (PS:这部分我只改了test_model == 1的 e 数据集，因为用的这个，
　　　　　　　　self.image_root = './ECSSD/'  # todo 去掉这个Imgs不然会重复 Imgs/Imgs）
 

  1. class ImageDataTest(data.Dataset):
  2.     def __init__(self, test_mode=1, sal_mode='e'):
  3.         if test_mode == 0:
  4.             # self.image_root = '/home/liuj/dataset/saliency_test/ECSSD/Imgs/'
  5.             # self.image_source = '/home/liuj/dataset/saliency_test/ECSSD/test.lst'
  6.             self.image_root = '/home/liuj/dataset/HED-BSDS_PASCAL/HED-BSDS/test/'
  7.             self.image_source = '/home/liuj/dataset/HED-BSDS_PASCAL/HED-BSDS/test.lst'
  8.  
  9.         elif test_mode == 1:
  10.             if sal_mode == 'e':
  11.                 # self.image_root = '/home/liuj/dataset/saliency_test/ECSSD/Imgs/'  # todo
  12.                 # self.image_root = './ECSSD/Imgs/'
  13.                 self.image_root = './ECSSD/'
  14.                 # self.image_source = '/home/liuj/dataset/saliency_test/ECSSD/test.lst'
  15.                 self.image_source = './ECSSD/test.lst'
  16.                 # self.test_fold = '/media/ubuntu/disk/Result/saliency/ECSSD/'
  17.                 self.test_fold = './Result/saliency/ECSSD/'

./ECSSD/test.lst　因为github没有提供，是我自己写的，如下左边.
目录放置结构如右
  
这样才对，上面是用来训练的

然后输出图片要注意，name[:-4]要改成name[3:-4],这样会生成一个s文件夹

最终路径如下　./Result/saliency/ECSSD/EGNet_ResNet50/s/806.png

５　下面是完整报错内容:（下述问题,通过上面办法已经解决）

  1. ​
  2.  
  3. (env_py36) hp@hp-X599:~/zjc/nk_PyCharm/PyCharm_project/EGNet-master$ python3 run.py --mode test --sal_mode e
  4. trueUnify bone part
  5. TUN_bone(
  6.   (convert): ConvertLayer(
  7.     (convert0): ModuleList(
  8.       (0): Sequential(
  9.         (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  10.         (1): ReLU(inplace)
  11.       )
  12.       (1): Sequential(
  13.         (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  14.         (1): ReLU(inplace)
  15.       )
  16.       (2): Sequential(
  17.         (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  18.         (1): ReLU(inplace)
  19.       )
  20.       (3): Sequential(
  21.         (0): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  22.         (1): ReLU(inplace)
  23.       )
  24.       (4): Sequential(
  25.         (0): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  26.         (1): ReLU(inplace)
  27.       )
  28.     )
  29.   )
  30.   (base): ResNet(
  31.     (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
  32.     (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  33.     (relu): ReLU(inplace)
  34.     (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=True)
  35.     (layer1): Sequential(
  36.       (0): Bottleneck(
  37.         (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  38.         (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  39.         (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  40.         (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  41.         (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  42.         (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  43.         (relu): ReLU(inplace)
  44.         (downsample): Sequential(
  45.           (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  46.           (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  47.         )
  48.       )
  49.       (1): Bottleneck(
  50.         (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  51.         (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  52.         (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  53.         (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  54.         (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  55.         (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  56.         (relu): ReLU(inplace)
  57.       )
  58.       (2): Bottleneck(
  59.         (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  60.         (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  61.         (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  62.         (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  63.         (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  64.         (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  65.         (relu): ReLU(inplace)
  66.       )
  67.     )
  68.     (layer2): Sequential(
  69.       (0): Bottleneck(
  70.         (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
  71.         (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  72.         (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  73.         (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  74.         (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  75.         (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  76.         (relu): ReLU(inplace)
  77.         (downsample): Sequential(
  78.           (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
  79.           (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  80.         )
  81.       )
  82.       (1): Bottleneck(
  83.         (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  84.         (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  85.         (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  86.         (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  87.         (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  88.         (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  89.         (relu): ReLU(inplace)
  90.       )
  91.       (2): Bottleneck(
  92.         (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  93.         (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  94.         (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  95.         (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  96.         (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  97.         (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  98.         (relu): ReLU(inplace)
  99.       )
  100.       (3): Bottleneck(
  101.         (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  102.         (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  103.         (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  104.         (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  105.         (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  106.         (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  107.         (relu): ReLU(inplace)
  108.       )
  109.     )
  110.     (layer3): Sequential(
  111.       (0): Bottleneck(
  112.         (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
  113.         (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  114.         (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  115.         (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  116.         (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  117.         (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  118.         (relu): ReLU(inplace)
  119.         (downsample): Sequential(
  120.           (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
  121.           (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  122.         )
  123.       )
  124.       (1): Bottleneck(
  125.         (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  126.         (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  127.         (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  128.         (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  129.         (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  130.         (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  131.         (relu): ReLU(inplace)
  132.       )
  133.       (2): Bottleneck(
  134.         (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  135.         (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  136.         (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  137.         (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  138.         (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  139.         (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  140.         (relu): ReLU(inplace)
  141.       )
  142.       (3): Bottleneck(
  143.         (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  144.         (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  145.         (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  146.         (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  147.         (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  148.         (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  149.         (relu): ReLU(inplace)
  150.       )
  151.       (4): Bottleneck(
  152.         (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  153.         (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  154.         (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  155.         (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  156.         (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  157.         (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  158.         (relu): ReLU(inplace)
  159.       )
  160.       (5): Bottleneck(
  161.         (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  162.         (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  163.         (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  164.         (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  165.         (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
  166.         (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  167.         (relu): ReLU(inplace)
  168.       )
  169.     )
  170.     (layer4): Sequential(
  171.       (0): Bottleneck(
  172.         (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  173.         (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  174.         (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False)
  175.         (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  176.         (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
  177.         (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  178.         (relu): ReLU(inplace)
  179.         (downsample): Sequential(
  180.           (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
  181.           (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  182.         )
  183.       )
  184.       (1): Bottleneck(
  185.         (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  186.         (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  187.         (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False)
  188.         (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  189.         (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
  190.         (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  191.         (relu): ReLU(inplace)
  192.       )
  193.       (2): Bottleneck(
  194.         (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
  195.         (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  196.         (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(2, 2), dilation=(2, 2), bias=False)
  197.         (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  198.         (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
  199.         (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  200.         (relu): ReLU(inplace)
  201.       )
  202.     )
  203.   )
  204.   (merge1): MergeLayer1(
  205.     (trans): ModuleList(
  206.       (0): Sequential(
  207.         (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  208.         (1): ReLU(inplace)
  209.       )
  210.       (1): Sequential(
  211.         (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
  212.         (1): ReLU(inplace)
  213.       )
  214.       (2): Sequential(
  215.         (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  216.         (1): ReLU(inplace)
  217.       )
  218.     )
  219.     (up): ModuleList(
  220.       (0): Sequential(
  221.         (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  222.         (1): ReLU(inplace)
  223.         (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  224.         (3): ReLU(inplace)
  225.         (4): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  226.         (5): ReLU(inplace)
  227.       )
  228.       (1): Sequential(
  229.         (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  230.         (1): ReLU(inplace)
  231.         (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  232.         (3): ReLU(inplace)
  233.         (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  234.         (5): ReLU(inplace)
  235.       )
  236.       (2): Sequential(
  237.         (0): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  238.         (1): ReLU(inplace)
  239.         (2): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  240.         (3): ReLU(inplace)
  241.         (4): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  242.         (5): ReLU(inplace)
  243.       )
  244.       (3): Sequential(
  245.         (0): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  246.         (1): ReLU(inplace)
  247.         (2): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  248.         (3): ReLU(inplace)
  249.         (4): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  250.         (5): ReLU(inplace)
  251.       )
  252.       (4): Sequential(
  253.         (0): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3))
  254.         (1): ReLU(inplace)
  255.         (2): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3))
  256.         (3): ReLU(inplace)
  257.         (4): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3))
  258.         (5): ReLU(inplace)
  259.       )
  260.     )
  261.     (score): ModuleList(
  262.       (0): Conv2d(128, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  263.       (1): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  264.       (2): Conv2d(512, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  265.       (3): Conv2d(512, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  266.       (4): Conv2d(512, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  267.     )
  268.     (relu): ReLU()
  269.   )
  270.   (merge2): MergeLayer2(
  271.     (trans): ModuleList(
  272.       (0): ModuleList(
  273.         (0): Sequential(
  274.           (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  275.           (1): ReLU(inplace)
  276.         )
  277.         (1): Sequential(
  278.           (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  279.           (1): ReLU(inplace)
  280.         )
  281.         (2): Sequential(
  282.           (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  283.           (1): ReLU(inplace)
  284.         )
  285.         (3): Sequential(
  286.           (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  287.           (1): ReLU(inplace)
  288.         )
  289.       )
  290.     )
  291.     (up): ModuleList(
  292.       (0): ModuleList(
  293.         (0): Sequential(
  294.           (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  295.           (1): ReLU(inplace)
  296.           (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  297.           (3): ReLU(inplace)
  298.           (4): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  299.           (5): ReLU(inplace)
  300.         )
  301.         (1): Sequential(
  302.           (0): Conv2d(128, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  303.           (1): ReLU(inplace)
  304.           (2): Conv2d(128, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  305.           (3): ReLU(inplace)
  306.           (4): Conv2d(128, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  307.           (5): ReLU(inplace)
  308.         )
  309.         (2): Sequential(
  310.           (0): Conv2d(128, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  311.           (1): ReLU(inplace)
  312.           (2): Conv2d(128, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  313.           (3): ReLU(inplace)
  314.           (4): Conv2d(128, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  315.           (5): ReLU(inplace)
  316.         )
  317.         (3): Sequential(
  318.           (0): Conv2d(128, 128, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3))
  319.           (1): ReLU(inplace)
  320.           (2): Conv2d(128, 128, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3))
  321.           (3): ReLU(inplace)
  322.           (4): Conv2d(128, 128, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3))
  323.           (5): ReLU(inplace)
  324.         )
  325.       )
  326.     )
  327.     (score): ModuleList(
  328.       (0): ModuleList(
  329.         (0): Conv2d(128, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  330.         (1): Conv2d(128, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  331.         (2): Conv2d(128, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  332.         (3): Conv2d(128, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  333.       )
  334.     )
  335.     (final_score): Sequential(
  336.       (0): Conv2d(128, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  337.       (1): ReLU(inplace)
  338.       (2): Conv2d(128, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  339.     )
  340.     (relu): ReLU()
  341.   )
  342. )
  343. The number of parameters: 111692618
  344. Loading pre-trained model from ./epoch_resnet.pth...
  345. File Not Exists
  346. File Not Exists
  347. File Not Exists
  348. File Not Exists
  349. File Not Exists
  350. File Not Exists
  351. Traceback (most recent call last):
  352.   File "run.py", line 69, in <module>
  353. File Not Exists
  354. File Not Exists
  355.     main(config)
  356.   File "run.py", line 23, in main
  357.     test.test(test_mode=config.test_mode)
  358.   File "/home/hp/zjc/nk_PyCharm/PyCharm_project/EGNet-master/solver.py", line 109, in test
  359.     for i, data_batch in enumerate(self.test_loader):
  360.   File "/home/hp/miniconda3/envs/env_py36/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 336, in __next__
  361.     return self._process_next_batch(batch)
  362.   File "/home/hp/miniconda3/envs/env_py36/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch
  363.     raise batch.exc_type(batch.exc_msg)
  364. ValueError: Traceback (most recent call last):
  365.   File "/home/hp/miniconda3/envs/env_py36/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop
  366.     samples = collate_fn([dataset[i] for i in batch_indices])
  367.   File "/home/hp/miniconda3/envs/env_py36/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 106, in <listcomp>
  368.     samples = collate_fn([dataset[i] for i in batch_indices])
  369.   File "/home/hp/zjc/nk_PyCharm/PyCharm_project/EGNet-master/dataset.py", line 99, in __getitem__
  370.     image, im_size = load_image_test(os.path.join(self.image_root, self.image_list[item]))
  371.   File "/home/hp/zjc/nk_PyCharm/PyCharm_project/EGNet-master/dataset.py", line 145, in load_image_test
  372.     in_ -= np.array((104.00699, 116.66877, 122.67892))
  373. ValueError: non-broadcastable output operand with shape () doesn't match the broadcast shape (3,)
  375. File Not Exists
  378. ​

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/我家自动化/article/detail/370411
推荐阅读
相关标签

Copyright © 2003-2013 www.wpsshop.cn 版权所有，并保留所有权利。

  

闽ICP备14008679号