CODEWITHSUNDEEP
python-3.xnlptransfer-learningfast-ai
Ravikrn
Ravikrn

Reputation: 397

How to get penultimate layer output of fastai text model?

learn = text_classifier_learner(data_clas, AWD_LSTM, drop_mult=0.7)
learn.fit_one_cycle(1, 1e-2)

I have trained fastai model as above. I can get prediction as below

preds, targets = learn.get_preds()

But instead I want penultimate layer embeddings of model learn (This practise is common for CNN models). Could you help me how to do it?

Upvotes: 0

Views: 741

Answers (1)

Renard Korzeniowski
Renard Korzeniowski

Reputation: 1105

I'm not sure if you want a classifier but anyway...

learn.model gives you back the model architecture. Then learn.model[0] would be an encoder learn.model[1] the other part of the model.

Example:

To access first linear layer in SequentialEx (architecture below) you would do it using following command learn.model[0].layers[0].ff.layers[0]

SequentialRNN(
    (0): TransformerXL(
      (encoder): Embedding(60004, 410)
      (pos_enc): PositionalEncoding()
      (drop_emb): Dropout(p=0.03)
      (layers): ModuleList(
        (0): DecoderLayer(
          (mhra): MultiHeadRelativeAttention(
            (attention): Linear(in_features=410, out_features=1230, bias=False)
            (out): Linear(in_features=410, out_features=410, bias=False)
            (drop_att): Dropout(p=0.03)
            (drop_res): Dropout(p=0.03)
            (ln): LayerNorm(torch.Size([410]), eps=1e-05, elementwise_affine=True)
            (r_attn): Linear(in_features=410, out_features=410, bias=False)
          )
          (ff): SequentialEx(
            (layers): ModuleList(
              (0): Linear(in_features=410, out_features=2100, bias=True)
              (1): ReLU(inplace)
              (2): Dropout(p=0.03)
              (3): Linear(in_features=2100, out_features=410, bias=True)
              (4): Dropout(p=0.03)
              (5): MergeLayer()
              (6): LayerNorm(torch.Size([410]), eps=1e-05, elementwise_affine=True)
            )
          )
        )

Upvotes: 1

Related Questions