I got following error: (base) yu@64:~/cv2/YOWO$ python video_mAP.py

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us
error with original video ,about wei-tim/yowo

Comments (9)

okankop commented on July 19, 2024
We have fixed the issue. You can pull the repo again and run your code!
from yowo.
onoderay commented on July 19, 2024
I got your update and tried again but I'm sorry, I got exactly same result
from yowo.
okankop commented on July 19, 2024
I believe, you are trying to feed a video to the network "/home/yuyonod/cv2/YOWO/test.avi". You should extract video frames and bring it to the dataset format to get it working!
from yowo.
onoderay commented on July 19, 2024
I'm sorry I converted avi to png then tired again but I got same error.

yuyonod$sh run_video_mAP_ucf.sh
DataParallel(
  (module): YOWO(
    (backbone_2d): Darknet(
      (models): ModuleList(
        (0): Sequential(
          (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky1): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        (2): Sequential(
          (conv2): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky2): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        (4): Sequential(
          (conv3): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky3): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (5): Sequential(
          (conv4): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky4): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (6): Sequential(
          (conv5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn5): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky5): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (7): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        (8): Sequential(
          (conv6): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky6): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (9): Sequential(
          (conv7): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn7): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky7): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (10): Sequential(
          (conv8): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky8): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (11): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        (12): Sequential(
          (conv9): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn9): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky9): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (13): Sequential(
          (conv10): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn10): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky10): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (14): Sequential(
          (conv11): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn11): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky11): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (15): Sequential(
          (conv12): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn12): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky12): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (16): Sequential(
          (conv13): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn13): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky13): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (17): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        (18): Sequential(
          (conv14): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn14): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky14): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (19): Sequential(
          (conv15): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn15): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky15): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (20): Sequential(
          (conv16): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn16): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky16): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (21): Sequential(
          (conv17): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn17): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky17): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (22): Sequential(
          (conv18): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn18): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky18): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (23): Sequential(
          (conv19): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn19): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky19): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (24): Sequential(
          (conv20): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn20): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky20): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (25): EmptyModule()
        (26): Sequential(
          (conv21): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn21): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky21): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (27): Reorg()
        (28): EmptyModule()
        (29): Sequential(
          (conv22): Conv2d(1280, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn22): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (leaky22): LeakyReLU(negative_slope=0.1, inplace=True)
        )
        (30): Sequential(
          (conv23): Conv2d(1024, 425, kernel_size=(1, 1), stride=(1, 1))
        )
        (31): RegionLoss()
      )
      (loss): RegionLoss()
    )
    (backbone_3d): ResNeXt(
      (conv1): Conv3d(3, 64, kernel_size=(7, 7, 7), stride=(1, 2, 2), padding=(3, 3, 3), bias=False)
      (bn1): BatchNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (maxpool): MaxPool3d(kernel_size=(3, 3, 3), stride=2, padding=1, dilation=1, ceil_mode=False)
      (layer1): Sequential(
        (0): ResNeXtBottleneck(
          (conv1): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv3d(64, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
            (1): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): ResNeXtBottleneck(
          (conv1): Conv3d(256, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (2): ResNeXtBottleneck(
          (conv1): Conv3d(256, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
      )
      (layer2): Sequential(
        (0): ResNeXtBottleneck(
          (conv1): Conv3d(256, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(256, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv3d(256, 512, kernel_size=(1, 1, 1), stride=(2, 2, 2), bias=False)
            (1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): ResNeXtBottleneck(
          (conv1): Conv3d(512, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(256, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (2): ResNeXtBottleneck(
          (conv1): Conv3d(512, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(256, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (3): ResNeXtBottleneck(
          (conv1): Conv3d(512, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(256, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
      )
      (layer3): Sequential(
        (0): ResNeXtBottleneck(
          (conv1): Conv3d(512, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(2, 2, 2), bias=False)
            (1): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (2): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (3): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (4): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (5): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (6): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (7): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (8): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (9): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (10): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (11): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (12): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (13): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (14): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (15): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (16): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (17): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (18): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (19): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (20): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (21): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (22): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 512, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(512, 512, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(512, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
      )
      (layer4): Sequential(
        (0): ResNeXtBottleneck(
          (conv1): Conv3d(1024, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(1024, 1024, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(1024, 2048, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (downsample): Sequential(
            (0): Conv3d(1024, 2048, kernel_size=(1, 1, 1), stride=(2, 2, 2), bias=False)
            (1): BatchNorm3d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): ResNeXtBottleneck(
          (conv1): Conv3d(2048, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(1024, 1024, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(1024, 2048, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
        (2): ResNeXtBottleneck(
          (conv1): Conv3d(2048, 1024, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn1): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv2): Conv3d(1024, 1024, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1), groups=32, bias=False)
          (bn2): BatchNorm3d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (conv3): Conv3d(1024, 2048, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)
          (bn3): BatchNorm3d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
        )
      )
    )
    (cfam): CFAMBlock(
      (conv_bn_relu1): Sequential(
        (0): Conv2d(2473, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU()
      )
      (conv_bn_relu2): Sequential(
        (0): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU()
      )
      (sc): CAM_Module(
        (softmax): Softmax(dim=-1)
      )
      (conv_bn_relu3): Sequential(
        (0): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU()
      )
      (conv_out): Sequential(
        (0): Dropout2d(p=0.1, inplace=False)
        (1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
      )
    )
    (conv_final): Conv2d(1024, 145, kernel_size=(1, 1), stride=(1, 1), bias=False)
  )
)
===================================================================
loading checkpoint /home/yuyonod/cv4/YOWO/models/yowo_ucf101-24_16f_best_fmap_08749.pth
===================================================================
/home/yuyonod/cv4/YOWO/result/test_1044.png

/home/yuyonod/cv4/YOWO/result/test_0389.png

/home/yuyonod/cv4/YOWO/result/test_0995.png

/home/yuyonod/cv4/YOWO/result/test_0682.png

/home/yuyonod/cv4/YOWO/result/test_1433.png

/home/yuyonod/cv4/YOWO/result/test_0356.png

/home/yuyonod/cv4/YOWO/result/test_0484.png

/home/yuyonod/cv4/YOWO/result/test_1439.png

/home/yuyonod/cv4/YOWO/result/test_0672.png

/home/yuyonod/cv4/YOWO/result/test_0633.png

/home/yuyonod/cv4/YOWO/result/test_0055.png

/home/yuyonod/cv4/YOWO/result/test_1415.png

/home/yuyonod/cv4/YOWO/result/test_0094.png

/home/yuyonod/cv4/YOWO/result/test_0257.png

/home/yuyonod/cv4/YOWO/result/test_0880.png

/home/yuyonod/cv4/YOWO/result/test_1457.png

/home/yuyonod/cv4/YOWO/result/test_1250.png

/home/yuyonod/cv4/YOWO/result/test_0427.png

/home/yuyonod/cv4/YOWO/result/test_1484.png

/home/yuyonod/cv4/YOWO/result/test_1412.png

/home/yuyonod/cv4/YOWO/result/test_1207.png

/home/yuyonod/cv4/YOWO/result/test_1378.png

/home/yuyonod/cv4/YOWO/result/test_0195.png

/home/yuyonod/cv4/YOWO/result/test_0373.png

/home/yuyonod/cv4/YOWO/result/test_0878.png

/home/yuyonod/cv4/YOWO/result/test_1251.png

/home/yuyonod/cv4/YOWO/result/test_0247.png

/home/yuyonod/cv4/YOWO/result/test_0413.png

/home/yuyonod/cv4/YOWO/result/test_1074.png

/home/yuyonod/cv4/YOWO/result/test_1382.png

/home/yuyonod/cv4/YOWO/result/test_0867.png

/home/yuyonod/cv4/YOWO/result/test_0252.png

/home/yuyonod/cv4/YOWO/result/test_0065.png

/home/yuyonod/cv4/YOWO/result/test_1296.png

/home/yuyonod/cv4/YOWO/result/test_1155.png

/home/yuyonod/cv4/YOWO/result/test_1480.png

/home/yuyonod/cv4/YOWO/result/test_0918.png

/home/yuyonod/cv4/YOWO/result/test_1028.png

/home/yuyonod/cv4/YOWO/result/test_0061.png

/home/yuyonod/cv4/YOWO/result/test_0585.png

/home/yuyonod/cv4/YOWO/result/test_1065.png

/home/yuyonod/cv4/YOWO/result/test_0837.png

/home/yuyonod/cv4/YOWO/result/test_0351.png

/home/yuyonod/cv4/YOWO/result/test_0580.png

/home/yuyonod/cv4/YOWO/result/test_0098.png

/home/yuyonod/cv4/YOWO/result/test_0806.png

/home/yuyonod/cv4/YOWO/result/test_1416.png

/home/yuyonod/cv4/YOWO/result/test_0856.png

/home/yuyonod/cv4/YOWO/result/test_1072.png

/home/yuyonod/cv4/YOWO/result/test_1056.png

/home/yuyonod/cv4/YOWO/result/test_0209.png

/home/yuyonod/cv4/YOWO/result/test_1081.png

/home/yuyonod/cv4/YOWO/result/test_0444.png

/home/yuyonod/cv4/YOWO/result/test_0996.png

/home/yuyonod/cv4/YOWO/result/test_1254.png

/home/yuyonod/cv4/YOWO/result/test_0003.png

/home/yuyonod/cv4/YOWO/result/test_1402.png

/home/yuyonod/cv4/YOWO/result/test_0210.png

/home/yuyonod/cv4/YOWO/result/test_0647.png

/home/yuyonod/cv4/YOWO/result/test_0275.png

/home/yuyonod/cv4/YOWO/result/test_0525.png

/home/yuyonod/cv4/YOWO/result/test_0962.png

/home/yuyonod/cv4/YOWO/result/test_0591.png

/home/yuyonod/cv4/YOWO/result/test_0538.png

/home/yuyonod/cv4/YOWO/result/test_0924.png

/home/yuyonod/cv4/YOWO/result/test_1003.png

/home/yuyonod/cv4/YOWO/result/test_1118.png

/home/yuyonod/cv4/YOWO/result/test_1238.png

/home/yuyonod/cv4/YOWO/result/test_0552.png

/home/yuyonod/cv4/YOWO/result/test_0589.png

/home/yuyonod/cv4/YOWO/result/test_1358.png

/home/yuyonod/cv4/YOWO/result/test_0833.png

/home/yuyonod/cv4/YOWO/result/test_0448.png

/home/yuyonod/cv4/YOWO/result/test_1163.png

/home/yuyonod/cv4/YOWO/result/test_0203.png

/home/yuyonod/cv4/YOWO/result/test_0157.png

/home/yuyonod/cv4/YOWO/result/test_1199.png

/home/yuyonod/cv4/YOWO/result/test_0062.png

/home/yuyonod/cv4/YOWO/result/test_0167.png

/home/yuyonod/cv4/YOWO/result/test_0053.png

/home/yuyonod/cv4/YOWO/result/test_0221.png

/home/yuyonod/cv4/YOWO/result/test_1171.png

/home/yuyonod/cv4/YOWO/result/test_1366.png

/home/yuyonod/cv4/YOWO/result/test_0882.png

/home/yuyonod/cv4/YOWO/result/test_0343.png

/home/yuyonod/cv4/YOWO/result/test_0001.png

/home/yuyonod/cv4/YOWO/result/test_0174.png

/home/yuyonod/cv4/YOWO/result/test_0054.png

/home/yuyonod/cv4/YOWO/result/test_1123.png

/home/yuyonod/cv4/YOWO/result/test_0304.png

/home/yuyonod/cv4/YOWO/result/test_1246.png

/home/yuyonod/cv4/YOWO/result/test_0963.png

/home/yuyonod/cv4/YOWO/result/test_1259.png

/home/yuyonod/cv4/YOWO/result/test_0438.png

/home/yuyonod/cv4/YOWO/result/test_0619.png

/home/yuyonod/cv4/YOWO/result/test_0790.png

/home/yuyonod/cv4/YOWO/result/test_1162.png

/home/yuyonod/cv4/YOWO/result/test_0168.png

/home/yuyonod/cv4/YOWO/result/test_0891.png

/home/yuyonod/cv4/YOWO/result/test_1075.png

/home/yuyonod/cv4/YOWO/result/test_0135.png

/home/yuyonod/cv4/YOWO/result/test_0676.png

/home/yuyonod/cv4/YOWO/result/test_0335.png

/home/yuyonod/cv4/YOWO/result/test_1292.png

/home/yuyonod/cv4/YOWO/result/test_1376.png

/home/yuyonod/cv4/YOWO/result/test_0641.png

/home/yuyonod/cv4/YOWO/result/test_0697.png

/home/yuyonod/cv4/YOWO/result/test_0089.png

/home/yuyonod/cv4/YOWO/result/test_1252.png

/home/yuyonod/cv4/YOWO/result/test_1336.png

/home/yuyonod/cv4/YOWO/result/test_0521.png

/home/yuyonod/cv4/YOWO/result/test_0649.png

/home/yuyonod/cv4/YOWO/result/test_1203.png

/home/yuyonod/cv4/YOWO/result/test_1228.png

/home/yuyonod/cv4/YOWO/result/test_0664.png

/home/yuyonod/cv4/YOWO/result/test_1368.png

/home/yuyonod/cv4/YOWO/result/test_0518.png

/home/yuyonod/cv4/YOWO/result/test_1178.png

/home/yuyonod/cv4/YOWO/result/test_1331.png

/home/yuyonod/cv4/YOWO/result/test_0280.png

/home/yuyonod/cv4/YOWO/result/test_0282.png

/home/yuyonod/cv4/YOWO/result/test_0645.png

/home/yuyonod/cv4/YOWO/result/test_1405.png

/home/yuyonod/cv4/YOWO/result/test_1466.png

/home/yuyonod/cv4/YOWO/result/test_0345.png

/home/yuyonod/cv4/YOWO/result/test_0447.png

/home/yuyonod/cv4/YOWO/result/test_0499.png

/home/yuyonod/cv4/YOWO/result/test_1521.png

/home/yuyonod/cv4/YOWO/result/test_1071.png

/home/yuyonod/cv4/YOWO/result/test_1312.png

/home/yuyonod/cv4/YOWO/result/test_0802.png

/home/yuyonod/cv4/YOWO/result/test_1363.png

/home/yuyonod/cv4/YOWO/result/test_1101.png

/home/yuyonod/cv4/YOWO/result/test_1100.png

/home/yuyonod/cv4/YOWO/result/test_0690.png

/home/yuyonod/cv4/YOWO/result/test_1173.png

/home/yuyonod/cv4/YOWO/result/test_0840.png

/home/yuyonod/cv4/YOWO/result/test_0709.png

/home/yuyonod/cv4/YOWO/result/test_1421.png

/home/yuyonod/cv4/YOWO/result/test_0394.png

/home/yuyonod/cv4/YOWO/result/test_0587.png

/home/yuyonod/cv4/YOWO/result/test_1242.png

/home/yuyonod/cv4/YOWO/result/test_0661.png

/home/yuyonod/cv4/YOWO/result/test_0173.png

/home/yuyonod/cv4/YOWO/result/test_0773.png

/home/yuyonod/cv4/YOWO/result/test_1400.png

/home/yuyonod/cv4/YOWO/result/test_0270.png

/home/yuyonod/cv4/YOWO/result/test_1011.png

/home/yuyonod/cv4/YOWO/result/test_0819.png

/home/yuyonod/cv4/YOWO/result/test_0584.png

/home/yuyonod/cv4/YOWO/result/test_0725.png

/home/yuyonod/cv4/YOWO/result/test_1383.png

/home/yuyonod/cv4/YOWO/result/test_0852.png

/home/yuyonod/cv4/YOWO/result/test_0892.png

/home/yuyonod/cv4/YOWO/result/test_0719.png

/home/yuyonod/cv4/YOWO/result/test_0246.png

/home/yuyonod/cv4/YOWO/result/test_1035.png

/home/yuyonod/cv4/YOWO/result/test_0059.png

/home/yuyonod/cv4/YOWO/result/test_0396.png

/home/yuyonod/cv4/YOWO/result/test_0501.png

/home/yuyonod/cv4/YOWO/result/test_0759.png

/home/yuyonod/cv4/YOWO/result/test_0079.png

/home/yuyonod/cv4/YOWO/result/test_1009.png

/home/yuyonod/cv4/YOWO/result/test_0981.png

/home/yuyonod/cv4/YOWO/result/test_0402.png

/home/yuyonod/cv4/YOWO/result/test_1436.png

/home/yuyonod/cv4/YOWO/result/test_0290.png

/home/yuyonod/cv4/YOWO/result/test_0750.png

/home/yuyonod/cv4/YOWO/result/test_1473.png

/home/yuyonod/cv4/YOWO/result/test_0654.png

/home/yuyonod/cv4/YOWO/result/test_0890.png

/home/yuyonod/cv4/YOWO/result/test_0475.png

/home/yuyonod/cv4/YOWO/result/test_1379.png

/home/yuyonod/cv4/YOWO/result/test_0917.png

/home/yuyonod/cv4/YOWO/result/test_0273.png

/home/yuyonod/cv4/YOWO/result/test_1364.png

/home/yuyonod/cv4/YOWO/result/test_0599.png

/home/yuyonod/cv4/YOWO/result/test_0040.png

/home/yuyonod/cv4/YOWO/result/test_0283.png

/home/yuyonod/cv4/YOWO/result/test_1245.png

/home/yuyonod/cv4/YOWO/result/test_1389.png

/home/yuyonod/cv4/YOWO/result/test_1372.png

/home/yuyonod/cv4/YOWO/result/test_0341.png

/home/yuyonod/cv4/YOWO/result/test_0866.png

/home/yuyonod/cv4/YOWO/result/test_0013.png

/home/yuyonod/cv4/YOWO/result/test_0740.png

/home/yuyonod/cv4/YOWO/result/test_1119.png

/home/yuyonod/cv4/YOWO/result/test_0845.png

/home/yuyonod/cv4/YOWO/result/test_1318.png

/home/yuyonod/cv4/YOWO/result/test_1053.png

/home/yuyonod/cv4/YOWO/result/test_1317.png

/home/yuyonod/cv4/YOWO/result/test_0931.png

/home/yuyonod/cv4/YOWO/result/test_0512.png

/home/yuyonod/cv4/YOWO/result/test_0696.png

/home/yuyonod/cv4/YOWO/result/test_0133.png

/home/yuyonod/cv4/YOWO/result/test_1022.png

/home/yuyonod/cv4/YOWO/result/test_0346.png

/home/yuyonod/cv4/YOWO/result/test_0397.png

/home/yuyonod/cv4/YOWO/result/test_0968.png

/home/yuyonod/cv4/YOWO/result/test_0031.png

/home/yuyonod/cv4/YOWO/result/test_0871.png

/home/yuyonod/cv4/YOWO/result/test_0189.png

/home/yuyonod/cv4/YOWO/result/test_1321.png

/home/yuyonod/cv4/YOWO/result/test_0946.png

/home/yuyonod/cv4/YOWO/result/test_0455.png

/home/yuyonod/cv4/YOWO/result/test_1161.png

/home/yuyonod/cv4/YOWO/result/test_1194.png

/home/yuyonod/cv4/YOWO/result/test_0194.png

/home/yuyonod/cv4/YOWO/result/test_0624.png

/home/yuyonod/cv4/YOWO/result/test_0041.png

/home/yuyonod/cv4/YOWO/result/test_0703.png

/home/yuyonod/cv4/YOWO/result/test_0193.png

/home/yuyonod/cv4/YOWO/result/test_0678.png

/home/yuyonod/cv4/YOWO/result/test_0976.png

/home/yuyonod/cv4/YOWO/result/test_1458.png

/home/yuyonod/cv4/YOWO/result/test_0727.png

/home/yuyonod/cv4/YOWO/result/test_0526.png

/home/yuyonod/cv4/YOWO/result/test_0197.png

/home/yuyonod/cv4/YOWO/result/test_0611.png

/home/yuyonod/cv4/YOWO/result/test_1214.png

/home/yuyonod/cv4/YOWO/result/test_1045.png

/home/yuyonod/cv4/YOWO/result/test_1322.png

/home/yuyonod/cv4/YOWO/result/test_0698.png

/home/yuyonod/cv4/YOWO/result/test_0177.png

/home/yuyonod/cv4/YOWO/result/test_0002.png

/home/yuyonod/cv4/YOWO/result/test_1307.png

/home/yuyonod/cv4/YOWO/result/test_0357.png

/home/yuyonod/cv4/YOWO/result/test_0028.png

/home/yuyonod/cv4/YOWO/result/test_0988.png

/home/yuyonod/cv4/YOWO/result/test_0110.png

/home/yuyonod/cv4/YOWO/result/test_0224.png

/home/yuyonod/cv4/YOWO/result/test_1232.png

/home/yuyonod/cv4/YOWO/result/test_0707.png

/home/yuyonod/cv4/YOWO/result/test_1271.png

/home/yuyonod/cv4/YOWO/result/test_0681.png

/home/yuyonod/cv4/YOWO/result/test_0228.png

/home/yuyonod/cv4/YOWO/result/test_1409.png

/home/yuyonod/cv4/YOWO/result/test_0797.png

/home/yuyonod/cv4/YOWO/result/test_1134.png

/home/yuyonod/cv4/YOWO/result/test_0032.png

/home/yuyonod/cv4/YOWO/result/test_0610.png

/home/yuyonod/cv4/YOWO/result/test_1420.png

/home/yuyonod/cv4/YOWO/result/test_0570.png

/home/yuyonod/cv4/YOWO/result/test_0240.png

/home/yuyonod/cv4/YOWO/result/test_0380.png

/home/yuyonod/cv4/YOWO/result/test_1411.png

/home/yuyonod/cv4/YOWO/result/test_0134.png

/home/yuyonod/cv4/YOWO/result/test_0265.png

/home/yuyonod/cv4/YOWO/result/test_0159.png

/home/yuyonod/cv4/YOWO/result/test_1169.png

/home/yuyonod/cv4/YOWO/result/test_0320.png

/home/yuyonod/cv4/YOWO/result/test_0643.png

/home/yuyonod/cv4/YOWO/result/test_1142.png

/home/yuyonod/cv4/YOWO/result/test_1185.png

/home/yuyonod/cv4/YOWO/result/test_0939.png

/home/yuyonod/cv4/YOWO/result/test_1277.png

/home/yuyonod/cv4/YOWO/result/test_1231.png

/home/yuyonod/cv4/YOWO/result/test_0384.png

/home/yuyonod/cv4/YOWO/result/test_0124.png

/home/yuyonod/cv4/YOWO/result/test_0457.png

/home/yuyonod/cv4/YOWO/result/test_0158.png

/home/yuyonod/cv4/YOWO/result/test_0588.png

/home/yuyonod/cv4/YOWO/result/test_0656.png

/home/yuyonod/cv4/YOWO/result/test_0534.png

/home/yuyonod/cv4/YOWO/result/test_1205.png

/home/yuyonod/cv4/YOWO/result/test_0937.png

/home/yuyonod/cv4/YOWO/result/test_0888.png

/home/yuyonod/cv4/YOWO/result/test_1511.png

/home/yuyonod/cv4/YOWO/result/test_0369.png

/home/yuyonod/cv4/YOWO/result/test_0674.png

/home/yuyonod/cv4/YOWO/result/test_0644.png

iou is:  0.05
Traceback (most recent call last):
  File "video_mAP.py", line 332, in <module>
    video_mAP_ucf()
  File "video_mAP.py", line 233, in video_mAP_ucf
    print(evaluate_videoAP(gt_videos, detected_boxes, CLASSES, iou_th, True))
  File "/home/yuyonod/cv4/YOWO/eval_results.py", line 236, in evaluate_videoAP
    pred_videos_format = imagebox_to_videts(all_boxes, CLASSES)
  File "/home/yuyonod/cv4/YOWO/eval_results.py", line 213, in imagebox_to_videts
    preVideo = os.path.dirname(keys[0])
IndexError: list index out of range
from yowo.
okankop commented on July 19, 2024
You are trying to test a video without having ground truth annotations. "video_mAP.py" is written to calculate video mAP results for the datasets. You should write a custom script by follow the validation procedure to get detection result, which contains predicted bounding box coordinates and labels in each frame. After that, you can try many tools like OpenCV to visualize them in the input video.
from yowo.
wei-tim commented on July 19, 2024
@onoderay
Hi,
video mAP is an evaluation metric for generated action tubes across a video. The exact definition is introduced in the paper "Finding Action Tubes" by Georgia Gkioxari.
from yowo.
okankop commented on July 19, 2024
I believe the issue is resolved!
from yowo.
abhigoku10 commented on July 19, 2024
@onoderay @okankop does the code run on gpu , is there any option to run it on cpu ??
from yowo.
ken292 commented on July 19, 2024
You are trying to test a video without having ground truth annotations. "video_mAP.py" is written to calculate video mAP results for the datasets. You should write a custom script by follow the validation procedure to get detection result, which contains predicted bounding box coordinates and labels in each frame. After that, you can try many tools like OpenCV to visualize them in the input video.
I am a bit confused, I can do Training and Validation with your code
but I couldn't use the video_mAP.py and get the same this as the problem in this thread. How can I fix this, can you please give me a clue.
Thank you very much
from yowo.
error with original video about yowo HOT 9 CLOSED

Comments (9)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent
