weixin_39664774
weixin_39664774
2020-12-01 19:57

darknet2onnx成功后,使用onnx2paddle报错

darknet模型:yolov3-darknet

darknet2onnx环境: onnx==1.2.1 python==2.7

darknet2onnx的过程: (darknet2onnx) qian:~/mayilong3/模型转换/darknet2onnx$ python2 yolov3_to_onnx.py Layer of type yolo not supported, skipping ONNX node generation. Layer of type yolo not supported, skipping ONNX node generation. Layer of type yolo not supported, skipping ONNX node generation. graph YOLOv3-608 ( %000_net[FLOAT, 1x3x608x608] ) initializers ( %001_convolutional_bn_scale[FLOAT, 32] %001_convolutional_bn_bias[FLOAT, 32] %001_convolutional_bn_mean[FLOAT, 32] %001_convolutional_bn_var[FLOAT, 32] %001_convolutional_conv_weights[FLOAT, 32x3x3x3] %002_convolutional_bn_scale[FLOAT, 64] %002_convolutional_bn_bias[FLOAT, 64] %002_convolutional_bn_mean[FLOAT, 64] %002_convolutional_bn_var[FLOAT, 64] %002_convolutional_conv_weights[FLOAT, 64x32x3x3] %003_convolutional_bn_scale[FLOAT, 32] %003_convolutional_bn_bias[FLOAT, 32] %003_convolutional_bn_mean[FLOAT, 32] %003_convolutional_bn_var[FLOAT, 32] %003_convolutional_conv_weights[FLOAT, 32x64x1x1] %004_convolutional_bn_scale[FLOAT, 64] %004_convolutional_bn_bias[FLOAT, 64] %004_convolutional_bn_mean[FLOAT, 64] %004_convolutional_bn_var[FLOAT, 64] %004_convolutional_conv_weights[FLOAT, 64x32x3x3] %006_convolutional_bn_scale[FLOAT, 128] %006_convolutional_bn_bias[FLOAT, 128] %006_convolutional_bn_mean[FLOAT, 128] %006_convolutional_bn_var[FLOAT, 128] %006_convolutional_conv_weights[FLOAT, 128x64x3x3] %007_convolutional_bn_scale[FLOAT, 64] %007_convolutional_bn_bias[FLOAT, 64] %007_convolutional_bn_mean[FLOAT, 64] %007_convolutional_bn_var[FLOAT, 64] %007_convolutional_conv_weights[FLOAT, 64x128x1x1] %008_convolutional_bn_scale[FLOAT, 128] %008_convolutional_bn_bias[FLOAT, 128] %008_convolutional_bn_mean[FLOAT, 128] %008_convolutional_bn_var[FLOAT, 128] %008_convolutional_conv_weights[FLOAT, 128x64x3x3] %010_convolutional_bn_scale[FLOAT, 64] %010_convolutional_bn_bias[FLOAT, 64] %010_convolutional_bn_mean[FLOAT, 64] %010_convolutional_bn_var[FLOAT, 64] %010_convolutional_conv_weights[FLOAT, 64x128x1x1] %011_convolutional_bn_scale[FLOAT, 128] %011_convolutional_bn_bias[FLOAT, 128] %011_convolutional_bn_mean[FLOAT, 128] %011_convolutional_bn_var[FLOAT, 128] %011_convolutional_conv_weights[FLOAT, 128x64x3x3] %013_convolutional_bn_scale[FLOAT, 256] %013_convolutional_bn_bias[FLOAT, 256] %013_convolutional_bn_mean[FLOAT, 256] %013_convolutional_bn_var[FLOAT, 256] %013_convolutional_conv_weights[FLOAT, 256x128x3x3] %014_convolutional_bn_scale[FLOAT, 128] %014_convolutional_bn_bias[FLOAT, 128] %014_convolutional_bn_mean[FLOAT, 128] %014_convolutional_bn_var[FLOAT, 128] %014_convolutional_conv_weights[FLOAT, 128x256x1x1] %015_convolutional_bn_scale[FLOAT, 256] %015_convolutional_bn_bias[FLOAT, 256] %015_convolutional_bn_mean[FLOAT, 256] %015_convolutional_bn_var[FLOAT, 256] %015_convolutional_conv_weights[FLOAT, 256x128x3x3] %017_convolutional_bn_scale[FLOAT, 128] %017_convolutional_bn_bias[FLOAT, 128] %017_convolutional_bn_mean[FLOAT, 128] %017_convolutional_bn_var[FLOAT, 128] %017_convolutional_conv_weights[FLOAT, 128x256x1x1] %018_convolutional_bn_scale[FLOAT, 256] %018_convolutional_bn_bias[FLOAT, 256] %018_convolutional_bn_mean[FLOAT, 256] %018_convolutional_bn_var[FLOAT, 256] %018_convolutional_conv_weights[FLOAT, 256x128x3x3] %020_convolutional_bn_scale[FLOAT, 128] %020_convolutional_bn_bias[FLOAT, 128] %020_convolutional_bn_mean[FLOAT, 128] %020_convolutional_bn_var[FLOAT, 128] %020_convolutional_conv_weights[FLOAT, 128x256x1x1] %021_convolutional_bn_scale[FLOAT, 256] %021_convolutional_bn_bias[FLOAT, 256] %021_convolutional_bn_mean[FLOAT, 256] %021_convolutional_bn_var[FLOAT, 256] %021_convolutional_conv_weights[FLOAT, 256x128x3x3] %023_convolutional_bn_scale[FLOAT, 128] %023_convolutional_bn_bias[FLOAT, 128] %023_convolutional_bn_mean[FLOAT, 128] %023_convolutional_bn_var[FLOAT, 128] %023_convolutional_conv_weights[FLOAT, 128x256x1x1] %024_convolutional_bn_scale[FLOAT, 256] %024_convolutional_bn_bias[FLOAT, 256] %024_convolutional_bn_mean[FLOAT, 256] %024_convolutional_bn_var[FLOAT, 256] %024_convolutional_conv_weights[FLOAT, 256x128x3x3] %026_convolutional_bn_scale[FLOAT, 128] %026_convolutional_bn_bias[FLOAT, 128] %026_convolutional_bn_mean[FLOAT, 128] %026_convolutional_bn_var[FLOAT, 128] %026_convolutional_conv_weights[FLOAT, 128x256x1x1] %027_convolutional_bn_scale[FLOAT, 256] %027_convolutional_bn_bias[FLOAT, 256] %027_convolutional_bn_mean[FLOAT, 256] %027_convolutional_bn_var[FLOAT, 256] %027_convolutional_conv_weights[FLOAT, 256x128x3x3] %029_convolutional_bn_scale[FLOAT, 128] %029_convolutional_bn_bias[FLOAT, 128] %029_convolutional_bn_mean[FLOAT, 128] %029_convolutional_bn_var[FLOAT, 128] %029_convolutional_conv_weights[FLOAT, 128x256x1x1] %030_convolutional_bn_scale[FLOAT, 256] %030_convolutional_bn_bias[FLOAT, 256] %030_convolutional_bn_mean[FLOAT, 256] %030_convolutional_bn_var[FLOAT, 256] %030_convolutional_conv_weights[FLOAT, 256x128x3x3] %032_convolutional_bn_scale[FLOAT, 128] %032_convolutional_bn_bias[FLOAT, 128] %032_convolutional_bn_mean[FLOAT, 128] %032_convolutional_bn_var[FLOAT, 128] %032_convolutional_conv_weights[FLOAT, 128x256x1x1] %033_convolutional_bn_scale[FLOAT, 256] %033_convolutional_bn_bias[FLOAT, 256] %033_convolutional_bn_mean[FLOAT, 256] %033_convolutional_bn_var[FLOAT, 256] %033_convolutional_conv_weights[FLOAT, 256x128x3x3] %035_convolutional_bn_scale[FLOAT, 128] %035_convolutional_bn_bias[FLOAT, 128] %035_convolutional_bn_mean[FLOAT, 128] %035_convolutional_bn_var[FLOAT, 128] %035_convolutional_conv_weights[FLOAT, 128x256x1x1] %036_convolutional_bn_scale[FLOAT, 256] %036_convolutional_bn_bias[FLOAT, 256] %036_convolutional_bn_mean[FLOAT, 256] %036_convolutional_bn_var[FLOAT, 256] %036_convolutional_conv_weights[FLOAT, 256x128x3x3] %038_convolutional_bn_scale[FLOAT, 512] %038_convolutional_bn_bias[FLOAT, 512] %038_convolutional_bn_mean[FLOAT, 512] %038_convolutional_bn_var[FLOAT, 512] %038_convolutional_conv_weights[FLOAT, 512x256x3x3] %039_convolutional_bn_scale[FLOAT, 256] %039_convolutional_bn_bias[FLOAT, 256] %039_convolutional_bn_mean[FLOAT, 256] %039_convolutional_bn_var[FLOAT, 256] %039_convolutional_conv_weights[FLOAT, 256x512x1x1] %040_convolutional_bn_scale[FLOAT, 512] %040_convolutional_bn_bias[FLOAT, 512] %040_convolutional_bn_mean[FLOAT, 512] %040_convolutional_bn_var[FLOAT, 512] %040_convolutional_conv_weights[FLOAT, 512x256x3x3] %042_convolutional_bn_scale[FLOAT, 256] %042_convolutional_bn_bias[FLOAT, 256] %042_convolutional_bn_mean[FLOAT, 256] %042_convolutional_bn_var[FLOAT, 256] %042_convolutional_conv_weights[FLOAT, 256x512x1x1] %043_convolutional_bn_scale[FLOAT, 512] %043_convolutional_bn_bias[FLOAT, 512] %043_convolutional_bn_mean[FLOAT, 512] %043_convolutional_bn_var[FLOAT, 512] %043_convolutional_conv_weights[FLOAT, 512x256x3x3] %045_convolutional_bn_scale[FLOAT, 256] %045_convolutional_bn_bias[FLOAT, 256] %045_convolutional_bn_mean[FLOAT, 256] %045_convolutional_bn_var[FLOAT, 256] %045_convolutional_conv_weights[FLOAT, 256x512x1x1] %046_convolutional_bn_scale[FLOAT, 512] %046_convolutional_bn_bias[FLOAT, 512] %046_convolutional_bn_mean[FLOAT, 512] %046_convolutional_bn_var[FLOAT, 512] %046_convolutional_conv_weights[FLOAT, 512x256x3x3] %048_convolutional_bn_scale[FLOAT, 256] %048_convolutional_bn_bias[FLOAT, 256] %048_convolutional_bn_mean[FLOAT, 256] %048_convolutional_bn_var[FLOAT, 256] %048_convolutional_conv_weights[FLOAT, 256x512x1x1] %049_convolutional_bn_scale[FLOAT, 512] %049_convolutional_bn_bias[FLOAT, 512] %049_convolutional_bn_mean[FLOAT, 512] %049_convolutional_bn_var[FLOAT, 512] %049_convolutional_conv_weights[FLOAT, 512x256x3x3] %051_convolutional_bn_scale[FLOAT, 256] %051_convolutional_bn_bias[FLOAT, 256] %051_convolutional_bn_mean[FLOAT, 256] %051_convolutional_bn_var[FLOAT, 256] %051_convolutional_conv_weights[FLOAT, 256x512x1x1] %052_convolutional_bn_scale[FLOAT, 512] %052_convolutional_bn_bias[FLOAT, 512] %052_convolutional_bn_mean[FLOAT, 512] %052_convolutional_bn_var[FLOAT, 512] %052_convolutional_conv_weights[FLOAT, 512x256x3x3] %054_convolutional_bn_scale[FLOAT, 256] %054_convolutional_bn_bias[FLOAT, 256] %054_convolutional_bn_mean[FLOAT, 256] %054_convolutional_bn_var[FLOAT, 256] %054_convolutional_conv_weights[FLOAT, 256x512x1x1] %055_convolutional_bn_scale[FLOAT, 512] %055_convolutional_bn_bias[FLOAT, 512] %055_convolutional_bn_mean[FLOAT, 512] %055_convolutional_bn_var[FLOAT, 512] %055_convolutional_conv_weights[FLOAT, 512x256x3x3] %057_convolutional_bn_scale[FLOAT, 256] %057_convolutional_bn_bias[FLOAT, 256] %057_convolutional_bn_mean[FLOAT, 256] %057_convolutional_bn_var[FLOAT, 256] %057_convolutional_conv_weights[FLOAT, 256x512x1x1] %058_convolutional_bn_scale[FLOAT, 512] %058_convolutional_bn_bias[FLOAT, 512] %058_convolutional_bn_mean[FLOAT, 512] %058_convolutional_bn_var[FLOAT, 512] %058_convolutional_conv_weights[FLOAT, 512x256x3x3] %060_convolutional_bn_scale[FLOAT, 256] %060_convolutional_bn_bias[FLOAT, 256] %060_convolutional_bn_mean[FLOAT, 256] %060_convolutional_bn_var[FLOAT, 256] %060_convolutional_conv_weights[FLOAT, 256x512x1x1] %061_convolutional_bn_scale[FLOAT, 512] %061_convolutional_bn_bias[FLOAT, 512] %061_convolutional_bn_mean[FLOAT, 512] %061_convolutional_bn_var[FLOAT, 512] %061_convolutional_conv_weights[FLOAT, 512x256x3x3] %063_convolutional_bn_scale[FLOAT, 1024] %063_convolutional_bn_bias[FLOAT, 1024] %063_convolutional_bn_mean[FLOAT, 1024] %063_convolutional_bn_var[FLOAT, 1024] %063_convolutional_conv_weights[FLOAT, 1024x512x3x3] %064_convolutional_bn_scale[FLOAT, 512] %064_convolutional_bn_bias[FLOAT, 512] %064_convolutional_bn_mean[FLOAT, 512] %064_convolutional_bn_var[FLOAT, 512] %064_convolutional_conv_weights[FLOAT, 512x1024x1x1] %065_convolutional_bn_scale[FLOAT, 1024] %065_convolutional_bn_bias[FLOAT, 1024] %065_convolutional_bn_mean[FLOAT, 1024] %065_convolutional_bn_var[FLOAT, 1024] %065_convolutional_conv_weights[FLOAT, 1024x512x3x3] %067_convolutional_bn_scale[FLOAT, 512] %067_convolutional_bn_bias[FLOAT, 512] %067_convolutional_bn_mean[FLOAT, 512] %067_convolutional_bn_var[FLOAT, 512] %067_convolutional_conv_weights[FLOAT, 512x1024x1x1] %068_convolutional_bn_scale[FLOAT, 1024] %068_convolutional_bn_bias[FLOAT, 1024] %068_convolutional_bn_mean[FLOAT, 1024] %068_convolutional_bn_var[FLOAT, 1024] %068_convolutional_conv_weights[FLOAT, 1024x512x3x3] %070_convolutional_bn_scale[FLOAT, 512] %070_convolutional_bn_bias[FLOAT, 512] %070_convolutional_bn_mean[FLOAT, 512] %070_convolutional_bn_var[FLOAT, 512] %070_convolutional_conv_weights[FLOAT, 512x1024x1x1] %071_convolutional_bn_scale[FLOAT, 1024] %071_convolutional_bn_bias[FLOAT, 1024] %071_convolutional_bn_mean[FLOAT, 1024] %071_convolutional_bn_var[FLOAT, 1024] %071_convolutional_conv_weights[FLOAT, 1024x512x3x3] %073_convolutional_bn_scale[FLOAT, 512] %073_convolutional_bn_bias[FLOAT, 512] %073_convolutional_bn_mean[FLOAT, 512] %073_convolutional_bn_var[FLOAT, 512] %073_convolutional_conv_weights[FLOAT, 512x1024x1x1] %074_convolutional_bn_scale[FLOAT, 1024] %074_convolutional_bn_bias[FLOAT, 1024] %074_convolutional_bn_mean[FLOAT, 1024] %074_convolutional_bn_var[FLOAT, 1024] %074_convolutional_conv_weights[FLOAT, 1024x512x3x3] %076_convolutional_bn_scale[FLOAT, 512] %076_convolutional_bn_bias[FLOAT, 512] %076_convolutional_bn_mean[FLOAT, 512] %076_convolutional_bn_var[FLOAT, 512] %076_convolutional_conv_weights[FLOAT, 512x1024x1x1] %077_convolutional_bn_scale[FLOAT, 1024] %077_convolutional_bn_bias[FLOAT, 1024] %077_convolutional_bn_mean[FLOAT, 1024] %077_convolutional_bn_var[FLOAT, 1024] %077_convolutional_conv_weights[FLOAT, 1024x512x3x3] %078_convolutional_bn_scale[FLOAT, 512] %078_convolutional_bn_bias[FLOAT, 512] %078_convolutional_bn_mean[FLOAT, 512] %078_convolutional_bn_var[FLOAT, 512] %078_convolutional_conv_weights[FLOAT, 512x1024x1x1] %079_convolutional_bn_scale[FLOAT, 1024] %079_convolutional_bn_bias[FLOAT, 1024] %079_convolutional_bn_mean[FLOAT, 1024] %079_convolutional_bn_var[FLOAT, 1024] %079_convolutional_conv_weights[FLOAT, 1024x512x3x3] %080_convolutional_bn_scale[FLOAT, 512] %080_convolutional_bn_bias[FLOAT, 512] %080_convolutional_bn_mean[FLOAT, 512] %080_convolutional_bn_var[FLOAT, 512] %080_convolutional_conv_weights[FLOAT, 512x1024x1x1] %081_convolutional_bn_scale[FLOAT, 1024] %081_convolutional_bn_bias[FLOAT, 1024] %081_convolutional_bn_mean[FLOAT, 1024] %081_convolutional_bn_var[FLOAT, 1024] %081_convolutional_conv_weights[FLOAT, 1024x512x3x3] %082_convolutional_conv_bias[FLOAT, 150] %082_convolutional_conv_weights[FLOAT, 150x1024x1x1] %085_convolutional_bn_scale[FLOAT, 256] %085_convolutional_bn_bias[FLOAT, 256] %085_convolutional_bn_mean[FLOAT, 256] %085_convolutional_bn_var[FLOAT, 256] %085_convolutional_conv_weights[FLOAT, 256x512x1x1] %088_convolutional_bn_scale[FLOAT, 256] %088_convolutional_bn_bias[FLOAT, 256] %088_convolutional_bn_mean[FLOAT, 256] %088_convolutional_bn_var[FLOAT, 256] %088_convolutional_conv_weights[FLOAT, 256x768x1x1] %089_convolutional_bn_scale[FLOAT, 512] %089_convolutional_bn_bias[FLOAT, 512] %089_convolutional_bn_mean[FLOAT, 512] %089_convolutional_bn_var[FLOAT, 512] %089_convolutional_conv_weights[FLOAT, 512x256x3x3] %090_convolutional_bn_scale[FLOAT, 256] %090_convolutional_bn_bias[FLOAT, 256] %090_convolutional_bn_mean[FLOAT, 256] %090_convolutional_bn_var[FLOAT, 256] %090_convolutional_conv_weights[FLOAT, 256x512x1x1] %091_convolutional_bn_scale[FLOAT, 512] %091_convolutional_bn_bias[FLOAT, 512] %091_convolutional_bn_mean[FLOAT, 512] %091_convolutional_bn_var[FLOAT, 512] %091_convolutional_conv_weights[FLOAT, 512x256x3x3] %092_convolutional_bn_scale[FLOAT, 256] %092_convolutional_bn_bias[FLOAT, 256] %092_convolutional_bn_mean[FLOAT, 256] %092_convolutional_bn_var[FLOAT, 256] %092_convolutional_conv_weights[FLOAT, 256x512x1x1] %093_convolutional_bn_scale[FLOAT, 512] %093_convolutional_bn_bias[FLOAT, 512] %093_convolutional_bn_mean[FLOAT, 512] %093_convolutional_bn_var[FLOAT, 512] %093_convolutional_conv_weights[FLOAT, 512x256x3x3] %094_convolutional_conv_bias[FLOAT, 150] %094_convolutional_conv_weights[FLOAT, 150x512x1x1] %097_convolutional_bn_scale[FLOAT, 128] %097_convolutional_bn_bias[FLOAT, 128] %097_convolutional_bn_mean[FLOAT, 128] %097_convolutional_bn_var[FLOAT, 128] %097_convolutional_conv_weights[FLOAT, 128x256x1x1] %100_convolutional_bn_scale[FLOAT, 128] %100_convolutional_bn_bias[FLOAT, 128] %100_convolutional_bn_mean[FLOAT, 128] %100_convolutional_bn_var[FLOAT, 128] %100_convolutional_conv_weights[FLOAT, 128x384x1x1] %101_convolutional_bn_scale[FLOAT, 256] %101_convolutional_bn_bias[FLOAT, 256] %101_convolutional_bn_mean[FLOAT, 256] %101_convolutional_bn_var[FLOAT, 256] %101_convolutional_conv_weights[FLOAT, 256x128x3x3] %102_convolutional_bn_scale[FLOAT, 128] %102_convolutional_bn_bias[FLOAT, 128] %102_convolutional_bn_mean[FLOAT, 128] %102_convolutional_bn_var[FLOAT, 128] %102_convolutional_conv_weights[FLOAT, 128x256x1x1] %103_convolutional_bn_scale[FLOAT, 256] %103_convolutional_bn_bias[FLOAT, 256] %103_convolutional_bn_mean[FLOAT, 256] %103_convolutional_bn_var[FLOAT, 256] %103_convolutional_conv_weights[FLOAT, 256x128x3x3] %104_convolutional_bn_scale[FLOAT, 128] %104_convolutional_bn_bias[FLOAT, 128] %104_convolutional_bn_mean[FLOAT, 128] %104_convolutional_bn_var[FLOAT, 128] %104_convolutional_conv_weights[FLOAT, 128x256x1x1] %105_convolutional_bn_scale[FLOAT, 256] %105_convolutional_bn_bias[FLOAT, 256] %105_convolutional_bn_mean[FLOAT, 256] %105_convolutional_bn_var[FLOAT, 256] %105_convolutional_conv_weights[FLOAT, 256x128x3x3] %106_convolutional_conv_bias[FLOAT, 150] %106_convolutional_conv_weights[FLOAT, 150x256x1x1] ) { %001_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %001_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %001_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %002_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [2, 2] %002_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %002_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %003_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %003_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %003_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %004_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %004_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %004_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %005_shortcut = Add(%004_convolutional_lrelu, %002_convolutional_lrelu) %006_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [2, 2] %006_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %006_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %007_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %007_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %007_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %008_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %008_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %008_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %009_shortcut = Add(%008_convolutional_lrelu, %006_convolutional_lrelu) %010_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %010_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %010_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %011_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %011_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %011_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %012_shortcut = Add(%011_convolutional_lrelu, %009_shortcut) %013_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [2, 2] %013_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %013_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %014_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %014_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %014_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %015_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %015_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %015_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %016_shortcut = Add(%015_convolutional_lrelu, %013_convolutional_lrelu) %017_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %017_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %017_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %018_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %018_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %018_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %019_shortcut = Add(%018_convolutional_lrelu, %016_shortcut) %020_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %020_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %020_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %021_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %021_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %021_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %022_shortcut = Add(%021_convolutional_lrelu, %019_shortcut) %023_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %023_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %023_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %024_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %024_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %024_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %025_shortcut = Add(%024_convolutional_lrelu, %022_shortcut) %026_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %026_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %026_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %027_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %027_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %027_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %028_shortcut = Add(%027_convolutional_lrelu, %025_shortcut) %029_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %029_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %029_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %030_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %030_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %030_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %031_shortcut = Add(%030_convolutional_lrelu, %028_shortcut) %032_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %032_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %032_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %033_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %033_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %033_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %034_shortcut = Add(%033_convolutional_lrelu, %031_shortcut) %035_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %035_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %035_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %036_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %036_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %036_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %037_shortcut = Add(%036_convolutional_lrelu, %034_shortcut) %038_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [2, 2] %038_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %038_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %039_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %039_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %039_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %040_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %040_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %040_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %041_shortcut = Add(%040_convolutional_lrelu, %038_convolutional_lrelu) %042_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %042_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %042_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %043_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %043_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %043_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %044_shortcut = Add(%043_convolutional_lrelu, %041_shortcut) %045_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %045_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %045_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %046_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %046_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %046_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %047_shortcut = Add(%046_convolutional_lrelu, %044_shortcut) %048_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %048_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %048_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %049_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %049_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %049_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %050_shortcut = Add(%049_convolutional_lrelu, %047_shortcut) %051_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %051_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %051_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %052_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %052_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %052_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %053_shortcut = Add(%052_convolutional_lrelu, %050_shortcut) %054_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %054_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %054_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %055_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %055_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %055_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %056_shortcut = Add(%055_convolutional_lrelu, %053_shortcut) %057_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %057_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %057_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %058_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %058_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %058_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %059_shortcut = Add(%058_convolutional_lrelu, %056_shortcut) %060_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %060_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %060_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %061_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %061_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %061_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %062_shortcut = Add(%061_convolutional_lrelu, %059_shortcut) %063_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [2, 2] %063_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %063_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %064_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %064_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %064_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %065_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %065_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %065_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %066_shortcut = Add(%065_convolutional_lrelu, %063_convolutional_lrelu) %067_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %067_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %067_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %068_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %068_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %068_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %069_shortcut = Add(%068_convolutional_lrelu, %066_shortcut) %070_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %070_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %070_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %071_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %071_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %071_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %072_shortcut = Add(%071_convolutional_lrelu, %069_shortcut) %073_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %073_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %073_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %074_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %074_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %074_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %075_shortcut = Add(%074_convolutional_lrelu, %072_shortcut) %076_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %076_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %076_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %077_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %077_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %077_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %078_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %078_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %078_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %079_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %079_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %079_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %080_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %080_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %080_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %081_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %081_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %081_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %082_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %085_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %085_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %085_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %086_upsample = Upsamplemode = u'nearest', scales = [1, 1, 2, 2] %087_route = Concataxis = 1 %088_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %088_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %088_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %089_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %089_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %089_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %090_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %090_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %090_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %091_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %091_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %091_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %092_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %092_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %092_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %093_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %093_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %093_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %094_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %097_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %097_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %097_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %098_upsample = Upsamplemode = u'nearest', scales = [1, 1, 2, 2] %099_route = Concataxis = 1 %100_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %100_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %100_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %101_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %101_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %101_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %102_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %102_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %102_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %103_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %103_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %103_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %104_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] %104_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %104_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %105_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [3, 3], strides = [1, 1] %105_convolutional_bn = BatchNormalizationepsilon = 9.99999974737875e-06, momentum = 0.990000009536743 %105_convolutional_lrelu = LeakyRelualpha = 0.100000001490116 %106_convolutional = Convauto_pad = u'SAME_LOWER', dilations = [1, 1], kernel_shape = [1, 1], strides = [1, 1] return %082_convolutional, %094_convolutional, %106_convolutional }

onnx2paddle环境: paddle==1.8.2 onnx==1.6.0 x2paddle==0.8.1

onnx2paddle转换过程: (paddle) qian:~/mayilong3/模型转换/darknet2onnx$ x2paddle --framework=onnx --model=yolov3_608.onnx --save_dir=yolov3_paddle paddle.version = 1.8.2 Now translating model from onnx to paddle. model ir_version: 3, op version: 7 shape inferencing ... shape inferenced. Now, onnx2paddle support convert onnx model opset_verison [9],opset_verison of your onnx model is 7, automatically treated as op_set: 9. Total nodes: 246 Nodes converting ... convert failed node:086_upsample, op_type is Upsample Traceback (most recent call last): File "/home/qian/anaconda3/envs/paddle/bin/x2paddle", line 33, in sys.exit(load_entry_point('x2paddle==0.8.1', 'console_scripts', 'x2paddle')()) File "/home/qian/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle-0.8.1-py3.7.egg/x2paddle/convert.py", line 268, in main onnx2paddle(args.model, args.save_dir, params_merge) File "/home/qian/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle-0.8.1-py3.7.egg/x2paddle/convert.py", line 185, in onnx2paddle mapper = ONNXOpMapper(model) File "/home/qian/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle-0.8.1-py3.7.egg/x2paddle/op_mapper/onnx2paddle/onnx_op_mapper.py", line 42, in init func(node) File "/home/qian/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle-0.8.1-py3.7.egg/x2paddle/op_mapper/onnx2paddle/opset9/opset.py", line 55, in run_mapping res = func(args, *kwargs) File "/home/qian/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle-0.8.1-py3.7.egg/x2paddle/op_mapper/onnx2paddle/opset9/opset.py", line 530, in Upsample self._interpolate(node) File "/home/qian/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle-0.8.1-py3.7.egg/x2paddle/op_mapper/onnx2paddle/opset9/opset.py", line 338, in _interpolate val_scales = self.graph.get_input_node(node, idx=1, copy=True) File "/home/qian/anaconda3/envs/paddle/lib/python3.7/site-packages/x2paddle-0.8.1-py3.7.egg/x2paddle/decoder/onnx_decoder.py", line 298, in get_input_node ipt_node = super(ONNXGraph, self).get_node(node.inputs[idx], copy) IndexError: list index out of range

darknet2onnx的源码是在网上找的,源地址为:https://blog.csdn.net/weixin_38106878/article/details/103714551

该提问来源于开源项目:PaddlePaddle/X2Paddle

  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 复制链接分享
  • 邀请回答

6条回答

  • weixin_39772420 weixin_39772420 5月前

    可以直接发onnx的模型吗?

    点赞 评论 复制链接分享
  • weixin_39664774 weixin_39664774 5月前

    已发,第一次发的压缩包里面是有onnx的模型的。

    点赞 评论 复制链接分享
  • weixin_39772420 weixin_39772420 5月前

    合入了对应修复的代码,可以重新拉一下develop然后手动安装。https://github.com/PaddlePaddle/X2Paddle#%E5%AE%89%E8%A3%85%E6%96%B9%E5%BC%8F%E4%B8%80%E6%8E%A8%E8%8D%90

    点赞 评论 复制链接分享
  • weixin_39664774 weixin_39664774 5月前

    十分感谢

    点赞 评论 复制链接分享
  • weixin_39772420 weixin_39772420 5月前

    麻烦把ONNX模型发到邮箱chen_lingchi.com,或者以网盘的方式给出来。

    点赞 评论 复制链接分享
  • weixin_39664774 weixin_39664774 5月前

    权重已发送过去了,麻烦您了。

    点赞 评论 复制链接分享

相关推荐