Skip to content

Missing in checkpoint  #5050

@SubWayss

Description

@SubWayss

I train the deeplab and use pre-trained model named 'xception_65',however,it remains me:
WARNING:tensorflow:Variable aspp2_depthwise/depthwise_weights/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/feature_projection0/weights missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv1_depthwise/BatchNorm/beta missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable image_pooling/BatchNorm/gamma missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp1_depthwise/depthwise_weights missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp0/BatchNorm/gamma missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_pointwise/BatchNorm/gamma missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable image_pooling/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp0/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv1_pointwise/BatchNorm/beta missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_pointwise/BatchNorm/beta missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable logits/semantic/weights missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_depthwise/BatchNorm/gamma missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv1_pointwise/weights/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv0_pointwise/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv1_depthwise/BatchNorm/moving_mean missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv0_depthwise/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_pointwise/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_depthwise/BatchNorm/moving_mean missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/feature_projection0/BatchNorm/moving_mean missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable logits/semantic/biases missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_pointwise/weights/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp0/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp1_pointwise/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp1_pointwise/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp1_pointwise/BatchNorm/gamma missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp1_depthwise/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/feature_projection0/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_pointwise/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv1_depthwise/BatchNorm/gamma missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp3_pointwise/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv0_depthwise/BatchNorm/moving_mean missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp3_depthwise/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv0_depthwise/BatchNorm/beta missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp3_depthwise/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable concat_projection/BatchNorm/gamma missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable image_pooling/BatchNorm/moving_variance missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp1_depthwise/BatchNorm/beta/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp3_pointwise/BatchNorm/beta missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp2_depthwise/BatchNorm/beta missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv0_pointwise/BatchNorm/moving_mean missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv0_pointwise/BatchNorm/gamma/Momentum missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable decoder/decoder_conv1_pointwise/BatchNorm/moving_mean missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp0/weights missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt WARNING:tensorflow:Variable aspp1_pointwise/BatchNorm/beta missing in checkpoint /home/vrview/models-master/research/deeplab/xception/model.ckpt
And when I trained on 1670 step, it causes a mistake like

  • INFO:tensorflow:global step 1640: loss = 0.8397 (0.360 sec/step)
  • INFO:tensorflow:global step 1650: loss = 1.2242 (0.358 sec/step)
  • INFO:tensorflow:global step 1660: loss = 0.9408 (0.352 sec/step)
  • INFO:tensorflow:global step 1670: loss = 0.8304 (0.357 sec/step)
  • INFO:tensorflow:global_step/sec: 2.79803

2018-08-10 09:16:21.108613: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Nan in summary histogram for: image_pooling/BatchNorm/moving_variance_1
[[Node: image_pooling/BatchNorm/moving_variance_1 = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](image_pooling/BatchNorm/moving_variance_1/tag, image_pooling/BatchNorm/moving_variance/read)]]
2018-08-10 09:16:21.109451: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Nan in summary histogram for: image_pooling/BatchNorm/moving_variance_1
[[Node: image_pooling/BatchNorm/moving_variance_1 = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](image_pooling/BatchNorm/moving_variance_1/tag, image_pooling/BatchNorm/moving_variance/read)]]
2018-08-10 09:16:21.109599: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Nan in summary histogram for: image_pooling/BatchNorm/moving_variance_1
[[Node: image_pooling/BatchNorm/moving_variance_1 = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](image_pooling/BatchNorm/moving_variance_1/tag, image_pooling/BatchNorm/moving_variance/read)]]
2018-08-10 09:16:21.124892: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Nan in summary histogram for: image_pooling/BatchNorm/moving_variance_1
[[Node: image_pooling/BatchNorm/moving_variance_1 = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](image_pooling/BatchNorm/moving_variance_1/tag, image_pooling/BatchNorm/moving_variance/read)]]
2018-08-10 09:16:21.125140: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Nan in summary histogram for: image_pooling/BatchNorm/moving_variance_1
[[Node: image_pooling/BatchNorm/moving_variance_1 = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](image_pooling/BatchNorm/moving_variance_1/tag, image_pooling/BatchNorm/moving_variance/read)]]

`

Activity

Dammi87

Dammi87 commented on Aug 10, 2018

@Dammi87

How are you loading the model?
I had issues when I did it manually, but it turned out it was because I wasn't using the arg_scope to load it.

Here is how I load Resnet 152 (I'm using it as an Encoder in a VAE, so I needed to have nicer access to it)

with slim.arg_scope(nets.resnet_v2.resnet_arg_scope()):
    logit, le_dict = nets.resnet_v2.resnet_v2_152(x,
                                                  num_classes=None,
                                                  is_training=mode == Modes.TRAIN,
                                                  global_pool=True,
                                                  output_stride=None,
                                                  spatial_squeeze=True,
                                                  reuse=None,
                                                  scope='resnet_v2_152')
Harshini-Gadige

Harshini-Gadige commented on Sep 25, 2018

@Harshini-Gadige

@SubWayss Hi, does this issue still exist ? If so, have you tried using arg_scope ?

wt-huang

wt-huang commented on Nov 1, 2018

@wt-huang

@Dammi87 is correct that arg_scope should work

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

      Development

      No branches or pull requests

        Participants

        @SubWayss@Dammi87@Harshini-Gadige@wt-huang

        Issue actions

          Missing in checkpoint · Issue #5050 · tensorflow/models