search

pudae / tensorflow-densenet

Tensorflow-DenseNet with ImageNet Pretrained Models
Apache License 2.0
169 stars 59 forks source link

Missing convolution biases in pre-trained checkpoints #21

Closed dmonn closed 5 years ago

dmonn commented 5 years ago

Using the inspect_checkpoint tool on the pretrained model, I can see that the convolutional layers miss their biases.

densenet169/dense_block4/conv_block4/x1/BatchNorm/beta (DT_FLOAT) [736]
densenet169/dense_block4/conv_block4/x1/BatchNorm/gamma (DT_FLOAT) [736]
densenet169/dense_block4/conv_block4/x1/BatchNorm/moving_mean (DT_FLOAT) [736]
densenet169/dense_block4/conv_block4/x1/BatchNorm/moving_variance (DT_FLOAT) [736]
densenet169/dense_block4/conv_block4/x1/Conv/weights (DT_FLOAT) [1,1,736,128]
densenet169/dense_block4/conv_block4/x2/BatchNorm/beta (DT_FLOAT) [128]
densenet169/dense_block4/conv_block4/x2/BatchNorm/gamma (DT_FLOAT) [128]
densenet169/dense_block4/conv_block4/x2/BatchNorm/moving_mean (DT_FLOAT) [128]
densenet169/dense_block4/conv_block4/x2/BatchNorm/moving_variance (DT_FLOAT) [128]
densenet169/dense_block4/conv_block4/x2/Conv/weights (DT_FLOAT) [3,3,128,32]

How were the Keras checkpoints converted? Did something go wrong?