in models/yolov4.py [0:0]
def __init__(self):
super().__init__()
self.tensor_1 = torch.tensor(8.0, dtype=torch.float32)
self.tensor_2 = torch.tensor([[0.5, 0.625], [0.875, 1.125], [1.125, 1.625]], dtype=torch.float32)
self.tensor_3 = torch.tensor(16.0, dtype=torch.float32)
self.tensor_4 = torch.tensor([[0.75, 0.9375], [0.875, 1.125], [1.0625, 1.3125]], dtype=torch.float32)
self.tensor_5 = torch.tensor(32.0, dtype=torch.float32)
self.tensor_6 = torch.tensor([[0.625, 0.78125], [0.8125, 1.03125], [1.09375, 1.46875]], dtype=torch.float32)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_0_0 = torch.nn.modules.conv.Conv2d(3, 32, 3, 2, 1, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_0_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_0_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_1_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_1_conv_3 = torch.nn.modules.conv.Conv2d(32, 16, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_0 = torch.nn.modules.conv.Conv2d(16, 96, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(96)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_3 = torch.nn.modules.conv.Conv2d(96, 96, 3, 2, 1, groups=96, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(96)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_6 = torch.nn.modules.conv.Conv2d(96, 24, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_2_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(24)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_0 = torch.nn.modules.conv.Conv2d(24, 144, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(144)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_3 = torch.nn.modules.conv.Conv2d(144, 144, 3, 1, 1, groups=144, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(144)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_6 = torch.nn.modules.conv.Conv2d(144, 24, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(24)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_3_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_0 = torch.nn.modules.conv.Conv2d(24, 144, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(144)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_3 = torch.nn.modules.conv.Conv2d(144, 144, 3, 2, 1, groups=144, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(144)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_6 = torch.nn.modules.conv.Conv2d(144, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_4_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_0 = torch.nn.modules.conv.Conv2d(32, 192, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(192)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_3 = torch.nn.modules.conv.Conv2d(192, 192, 3, 1, 1, groups=192, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(192)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_6 = torch.nn.modules.conv.Conv2d(192, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_5_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_0 = torch.nn.modules.conv.Conv2d(32, 192, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(192)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_3 = torch.nn.modules.conv.Conv2d(192, 192, 3, 1, 1, groups=192, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(192)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_6 = torch.nn.modules.conv.Conv2d(192, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_6_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_0 = torch.nn.modules.conv.Conv2d(32, 192, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(192)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_3 = torch.nn.modules.conv.Conv2d(192, 192, 3, 2, 1, groups=192, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(192)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_6 = torch.nn.modules.conv.Conv2d(192, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_7_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_0 = torch.nn.modules.conv.Conv2d(64, 384, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_3 = torch.nn.modules.conv.Conv2d(384, 384, 3, 1, 1, groups=384, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_6 = torch.nn.modules.conv.Conv2d(384, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_8_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_0 = torch.nn.modules.conv.Conv2d(64, 384, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_3 = torch.nn.modules.conv.Conv2d(384, 384, 3, 1, 1, groups=384, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_6 = torch.nn.modules.conv.Conv2d(384, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_9_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_0 = torch.nn.modules.conv.Conv2d(64, 384, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_3 = torch.nn.modules.conv.Conv2d(384, 384, 3, 1, 1, groups=384, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_6 = torch.nn.modules.conv.Conv2d(384, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_backbone__MobilenetV2Lite__submodule_features_10_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_0 = torch.nn.modules.conv.Conv2d(64, 384, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_3 = torch.nn.modules.conv.Conv2d(384, 384, 3, 1, 1, groups=384, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_6 = torch.nn.modules.conv.Conv2d(384, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_0_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_backbone_features_mnv3part_0_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_0 = torch.nn.modules.conv.Conv2d(64, 384, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_3 = torch.nn.modules.conv.Conv2d(384, 384, 3, 1, 1, groups=384, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_6 = torch.nn.modules.conv.Conv2d(384, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_1_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_backbone_features_mnv3part_1_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_0 = torch.nn.modules.conv.Conv2d(64, 384, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_3 = torch.nn.modules.conv.Conv2d(384, 384, 3, 1, 1, groups=384, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_6 = torch.nn.modules.conv.Conv2d(384, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_2_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_backbone_features_mnv3part_2_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_0 = torch.nn.modules.conv.Conv2d(64, 384, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_3 = torch.nn.modules.conv.Conv2d(384, 384, 3, 2, 1, groups=384, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(384)
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_6 = torch.nn.modules.conv.Conv2d(384, 96, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_3_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(96)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_0 = torch.nn.modules.conv.Conv2d(96, 576, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(576)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_3 = torch.nn.modules.conv.Conv2d(576, 576, 3, 1, 1, groups=576, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(576)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_6 = torch.nn.modules.conv.Conv2d(576, 96, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_4_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(96)
self._Build_Model__yolov4_backbone_features_mnv3part_4_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_0 = torch.nn.modules.conv.Conv2d(96, 576, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(576)
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_3 = torch.nn.modules.conv.Conv2d(576, 576, 3, 1, 1, groups=576, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(576)
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_5 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_6 = torch.nn.modules.conv.Conv2d(576, 96, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_features_mnv3part_5_conv_7 = torch.nn.modules.batchnorm.BatchNorm2d(96)
self._Build_Model__yolov4_backbone_features_mnv3part_5_qadd_0_activation_post_process = torch.nn.modules.linear.Identity()
self._Build_Model__yolov4_backbone_conv_0 = torch.nn.modules.conv.Conv2d(96, 160, 1, 1, 0, bias=False)
self._Build_Model__yolov4_backbone_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_backbone_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_spp_head_conv_0_conv_0 = torch.nn.modules.conv.Conv2d(160, 160, 3, 1, 1, groups=160, bias=False)
self._Build_Model__yolov4_spp_head_conv_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_spp_head_conv_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_spp_head_conv_0_conv_3 = torch.nn.modules.conv.Conv2d(160, 80, 1, 1, 0, bias=False)
self._Build_Model__yolov4_spp_head_conv_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_spp_head_conv_1_conv_0 = torch.nn.modules.conv.Conv2d(80, 80, 3, 1, 1, groups=80, bias=False)
self._Build_Model__yolov4_spp_head_conv_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_spp_head_conv_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_spp_head_conv_1_conv_3 = torch.nn.modules.conv.Conv2d(80, 160, 1, 1, 0, bias=False)
self._Build_Model__yolov4_spp_head_conv_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_spp_head_conv_2_conv_0 = torch.nn.modules.conv.Conv2d(160, 160, 3, 1, 1, groups=160, bias=False)
self._Build_Model__yolov4_spp_head_conv_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_spp_head_conv_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_spp_head_conv_2_conv_3 = torch.nn.modules.conv.Conv2d(160, 80, 1, 1, 0, bias=False)
self._Build_Model__yolov4_spp_head_conv_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_spp_maxpools_0 = torch.nn.modules.pooling.MaxPool2d(5, 1, 2)
self._Build_Model__yolov4_spp_maxpools_1 = torch.nn.modules.pooling.MaxPool2d(9, 1, 4)
self._Build_Model__yolov4_spp_maxpools_2 = torch.nn.modules.pooling.MaxPool2d(13, 1, 6)
self._Build_Model__yolov4_panet_feature_transform3_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_feature_transform3_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_feature_transform3_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_feature_transform3_conv_3 = torch.nn.modules.conv.Conv2d(32, 16, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_feature_transform3_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_panet_feature_transform4_conv_0 = torch.nn.modules.conv.Conv2d(64, 64, 3, 1, 1, groups=64, bias=False)
self._Build_Model__yolov4_panet_feature_transform4_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_feature_transform4_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_feature_transform4_conv_3 = torch.nn.modules.conv.Conv2d(64, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_feature_transform4_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv5_0_conv_0 = torch.nn.modules.conv.Conv2d(320, 320, 3, 1, 1, groups=320, bias=False)
self._Build_Model__yolov4_panet_downstream_conv5_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(320)
self._Build_Model__yolov4_panet_downstream_conv5_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv5_0_conv_3 = torch.nn.modules.conv.Conv2d(320, 80, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv5_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_downstream_conv5_1_conv_0 = torch.nn.modules.conv.Conv2d(80, 80, 3, 1, 1, groups=80, bias=False)
self._Build_Model__yolov4_panet_downstream_conv5_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_downstream_conv5_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv5_1_conv_3 = torch.nn.modules.conv.Conv2d(80, 160, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv5_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_panet_downstream_conv5_2_conv_0 = torch.nn.modules.conv.Conv2d(160, 160, 3, 1, 1, groups=160, bias=False)
self._Build_Model__yolov4_panet_downstream_conv5_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_panet_downstream_conv5_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv5_2_conv_3 = torch.nn.modules.conv.Conv2d(160, 80, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv5_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_resample5_4_upsample_0_conv_0 = torch.nn.modules.conv.Conv2d(80, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_resample5_4_upsample_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_resample5_4_upsample_0_conv_2 = torch.nn.modules.activation.LeakyReLU()
self._Build_Model__yolov4_panet_resample5_4_upsample_1 = torch.nn.modules.upsampling.Upsample(scale_factor=2)
self._Build_Model__yolov4_panet_downstream_conv4_0_conv_0 = torch.nn.modules.conv.Conv2d(64, 64, 3, 1, 1, groups=64, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_downstream_conv4_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv4_0_conv_3 = torch.nn.modules.conv.Conv2d(64, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv4_1_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv4_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv4_1_conv_3 = torch.nn.modules.conv.Conv2d(32, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_downstream_conv4_2_conv_0 = torch.nn.modules.conv.Conv2d(64, 64, 3, 1, 1, groups=64, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_downstream_conv4_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv4_2_conv_3 = torch.nn.modules.conv.Conv2d(64, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv4_3_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_3_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv4_3_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv4_3_conv_3 = torch.nn.modules.conv.Conv2d(32, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_3_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_downstream_conv4_4_conv_0 = torch.nn.modules.conv.Conv2d(64, 64, 3, 1, 1, groups=64, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_4_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_downstream_conv4_4_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv4_4_conv_3 = torch.nn.modules.conv.Conv2d(64, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv4_4_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_resample4_3_upsample_0_conv_0 = torch.nn.modules.conv.Conv2d(32, 16, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_resample4_3_upsample_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_panet_resample4_3_upsample_0_conv_2 = torch.nn.modules.activation.LeakyReLU()
self._Build_Model__yolov4_panet_resample4_3_upsample_1 = torch.nn.modules.upsampling.Upsample(scale_factor=2)
self._Build_Model__yolov4_panet_downstream_conv3_0_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv3_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv3_0_conv_3 = torch.nn.modules.conv.Conv2d(32, 16, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_panet_downstream_conv3_1_conv_0 = torch.nn.modules.conv.Conv2d(16, 16, 3, 1, 1, groups=16, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_panet_downstream_conv3_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv3_1_conv_3 = torch.nn.modules.conv.Conv2d(16, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv3_2_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv3_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv3_2_conv_3 = torch.nn.modules.conv.Conv2d(32, 16, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_panet_downstream_conv3_3_conv_0 = torch.nn.modules.conv.Conv2d(16, 16, 3, 1, 1, groups=16, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_3_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_panet_downstream_conv3_3_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv3_3_conv_3 = torch.nn.modules.conv.Conv2d(16, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_3_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv3_4_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_4_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_downstream_conv3_4_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_downstream_conv3_4_conv_3 = torch.nn.modules.conv.Conv2d(32, 16, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_downstream_conv3_4_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_panet_resample3_4_downsample_conv_0 = torch.nn.modules.conv.Conv2d(16, 32, 3, 2, 1, bias=False)
self._Build_Model__yolov4_panet_resample3_4_downsample_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_resample3_4_downsample_conv_2 = torch.nn.modules.activation.LeakyReLU()
self._Build_Model__yolov4_panet_upstream_conv4_0_conv_0 = torch.nn.modules.conv.Conv2d(64, 64, 3, 1, 1, groups=64, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_upstream_conv4_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv4_0_conv_3 = torch.nn.modules.conv.Conv2d(64, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_upstream_conv4_1_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_upstream_conv4_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv4_1_conv_3 = torch.nn.modules.conv.Conv2d(32, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_upstream_conv4_2_conv_0 = torch.nn.modules.conv.Conv2d(64, 64, 3, 1, 1, groups=64, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_upstream_conv4_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv4_2_conv_3 = torch.nn.modules.conv.Conv2d(64, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_upstream_conv4_3_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_3_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_upstream_conv4_3_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv4_3_conv_3 = torch.nn.modules.conv.Conv2d(32, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_3_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_upstream_conv4_4_conv_0 = torch.nn.modules.conv.Conv2d(64, 64, 3, 1, 1, groups=64, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_4_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_panet_upstream_conv4_4_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv4_4_conv_3 = torch.nn.modules.conv.Conv2d(64, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv4_4_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_panet_resample4_5_downsample_conv_0 = torch.nn.modules.conv.Conv2d(32, 80, 3, 2, 1, bias=False)
self._Build_Model__yolov4_panet_resample4_5_downsample_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_resample4_5_downsample_conv_2 = torch.nn.modules.activation.LeakyReLU()
self._Build_Model__yolov4_panet_upstream_conv5_0_conv_0 = torch.nn.modules.conv.Conv2d(160, 160, 3, 1, 1, groups=160, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_panet_upstream_conv5_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv5_0_conv_3 = torch.nn.modules.conv.Conv2d(160, 80, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_upstream_conv5_1_conv_0 = torch.nn.modules.conv.Conv2d(80, 80, 3, 1, 1, groups=80, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_1_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_upstream_conv5_1_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv5_1_conv_3 = torch.nn.modules.conv.Conv2d(80, 160, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_1_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_panet_upstream_conv5_2_conv_0 = torch.nn.modules.conv.Conv2d(160, 160, 3, 1, 1, groups=160, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_2_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_panet_upstream_conv5_2_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv5_2_conv_3 = torch.nn.modules.conv.Conv2d(160, 80, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_2_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_upstream_conv5_3_conv_0 = torch.nn.modules.conv.Conv2d(80, 80, 3, 1, 1, groups=80, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_3_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_panet_upstream_conv5_3_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv5_3_conv_3 = torch.nn.modules.conv.Conv2d(80, 160, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_3_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_panet_upstream_conv5_4_conv_0 = torch.nn.modules.conv.Conv2d(160, 160, 3, 1, 1, groups=160, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_4_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_panet_upstream_conv5_4_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_panet_upstream_conv5_4_conv_3 = torch.nn.modules.conv.Conv2d(160, 80, 1, 1, 0, bias=False)
self._Build_Model__yolov4_panet_upstream_conv5_4_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_predict_net_predict_conv_0_0_conv_0 = torch.nn.modules.conv.Conv2d(16, 16, 3, 1, 1, groups=16, bias=False)
self._Build_Model__yolov4_predict_net_predict_conv_0_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(16)
self._Build_Model__yolov4_predict_net_predict_conv_0_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_predict_net_predict_conv_0_0_conv_3 = torch.nn.modules.conv.Conv2d(16, 32, 1, 1, 0, bias=False)
self._Build_Model__yolov4_predict_net_predict_conv_0_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_predict_net_predict_conv_0_1 = torch.nn.modules.conv.Conv2d(32, 18, 1)
self._Build_Model__yolov4_predict_net_predict_conv_1_0_conv_0 = torch.nn.modules.conv.Conv2d(32, 32, 3, 1, 1, groups=32, bias=False)
self._Build_Model__yolov4_predict_net_predict_conv_1_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(32)
self._Build_Model__yolov4_predict_net_predict_conv_1_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_predict_net_predict_conv_1_0_conv_3 = torch.nn.modules.conv.Conv2d(32, 64, 1, 1, 0, bias=False)
self._Build_Model__yolov4_predict_net_predict_conv_1_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(64)
self._Build_Model__yolov4_predict_net_predict_conv_1_1 = torch.nn.modules.conv.Conv2d(64, 18, 1)
self._Build_Model__yolov4_predict_net_predict_conv_2_0_conv_0 = torch.nn.modules.conv.Conv2d(80, 80, 3, 1, 1, groups=80, bias=False)
self._Build_Model__yolov4_predict_net_predict_conv_2_0_conv_1 = torch.nn.modules.batchnorm.BatchNorm2d(80)
self._Build_Model__yolov4_predict_net_predict_conv_2_0_conv_2 = torch.nn.modules.activation.ReLU6(inplace=True)
self._Build_Model__yolov4_predict_net_predict_conv_2_0_conv_3 = torch.nn.modules.conv.Conv2d(80, 160, 1, 1, 0, bias=False)
self._Build_Model__yolov4_predict_net_predict_conv_2_0_conv_4 = torch.nn.modules.batchnorm.BatchNorm2d(160)
self._Build_Model__yolov4_predict_net_predict_conv_2_1 = torch.nn.modules.conv.Conv2d(160, 18, 1)