Firstly thanks for your brilliant model implement！
But when I try to transfer EfficientNet_v1 with efficientnet-b1_imagenet_1000.h5, there is a bug said "Layer #1 (named "conv2d_1") expects 2 weight(s), but the saved weights have 1 element(s)."
I load the checkpoint by model.load_weights(TRANSFER_MODEL_NAME, by_name = True)
The checkpoint was downloaded from https://github.com/qubvel/efficientnet/releases/download/v0.0.1/efficientnet-b1_imagenet_1000.h5
I know the which layer the bug come from but can not understand why this conv2D layer expect 2 weights and does the problem comes of the checkpoint or the code?
Firstly thanks for your brilliant model implement！
But when I try to transfer EfficientNet_v1 with efficientnet-b1_imagenet_1000.h5, there is a bug said "Layer #1 (named "conv2d_1") expects 2 weight(s), but the saved weights have 1 element(s)."
I load the checkpoint by model.load_weights(TRANSFER_MODEL_NAME, by_name = True)
The checkpoint was downloaded from https://github.com/qubvel/efficientnet/releases/download/v0.0.1/efficientnet-b1_imagenet_1000.h5
I know the which layer the bug come from but can not understand why this conv2D layer expect 2 weights and does the problem comes of the checkpoint or the code?