Hi，I meet some debug when i inference the model

[GitYesm]

What are the causes of the following problems?

Missing key(s) in state_dict: "quantizer.vq.layers.12._codebook.inited", "quantizer.vq.layers.12._codebook.cluster_size", "quantizer.vq.layers.12._codebook.embed", "quantizer.vq.layers.12._codebook.embed_avg", "quantizer.vq.layers.13._codebook.inited", "quantizer.vq.layers.13._codebook.cluster_size", "quantizer.vq.layers.13._codebook.embed", "quantizer.vq.layers.13._codebook.embed_avg", "quantizer.vq.layers.14._codebook.inited", "quantizer.vq.layers.14._codebook.cluster_size", "quantizer.vq.layers.14._codebook.embed", "quantizer.vq.layers.14._codebook.embed_avg", "quantizer.vq.layers.15._codebook.inited", "quantizer.vq.layers.15._codebook.cluster_size", "quantizer.vq.layers.15._codebook.embed", "quantizer.vq.layers.15._codebook.embed_avg", "quantizer.vq.layers.16._codebook.inited", "quantizer.vq.layers.16._codebook.cluster_size", "quantizer.vq.layers.16._codebook.embed", "quantizer.vq.layers.16._codebook.embed_avg", "quantizer.vq.layers.17._codebook.inited", "quantizer.vq.layers.17._codebook.cluster_size", "quantizer.vq.layers.17._codebook.embed", "quantizer.vq.layers.17._codebook.embed_avg", "quantizer.vq.layers.18._codebook.inited", "quantizer.vq.layers.18._codebook.cluster_size", "quantizer.vq.layers.18._codebook.embed", "quantizer.vq.layers.18._codebook.embed_avg", "quantizer.vq.layers.19._codebook.inited", "quantizer.vq.layers.19._codebook.cluster_size", "quantizer.vq.layers.19._codebook.embed", "quantizer.vq.layers.19._codebook.embed_avg", "quantizer.vq.layers.20._codebook.inited", "quantizer.vq.layers.20._codebook.cluster_size", "quantizer.vq.layers.20._codebook.embed", "quantizer.vq.layers.20._codebook.embed_avg", "quantizer.vq.layers.21._codebook.inited", "quantizer.vq.layers.21._codebook.cluster_size", "quantizer.vq.layers.21._codebook.embed", "quantizer.vq.layers.21._codebook.embed_avg", "quantizer.vq.layers.22._codebook.inited", "quantizer.vq.layers.22._codebook.cluster_size", "quantizer.vq.layers.22._codebook.embed", "quantizer.vq.layers.22._codebook.embed_avg", "quantizer.vq.layers.23._codebook.inited", "quantizer.vq.layers.23._codebook.cluster_size", "quantizer.vq.layers.23._codebook.embed", "quantizer.vq.layers.23._codebook.embed_avg".

[GitYesm]

target_bandwidths=[1, 2, 4, 8, 12] is Ok，but revise it will results the above error，like {1,1.5,2,4,8}

[lucidrains]

@GitYesm it is hard to know without seeing the full network

how does target_bandwidths feed into the initialization of VectorQuantize?

[GitYesm]

@GitYesm it is hard to know without seeing the full network

how does target_bandwidths feed into the initialization of VectorQuantize?

Sorry，I am trainning the speech coding task，according the target_bandwidths to compute the number of codebook.
Maybe the question reason from the init process of num_quantizer. Because i revise the target_bandwidths when i inference the pre-model.