is it possible to get the “confidence”/“logit”/“probability” measure of the DONUT model on the task of document type classification task and not just the final “class/token”?
I’ve seen that the last layer of the model is Linear:
(3): MBartDecoderLayer(
(self_attn): MBartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(activation_fn): GELUActivation()
(self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(encoder_attn): MBartAttention(
(k_proj): Linear(in_features=1024, out_features=1024, bias=True)
(v_proj): Linear(in_features=1024, out_features=1024, bias=True)
(q_proj): Linear(in_features=1024, out_features=1024, bias=True)
(out_proj): Linear(in_features=1024, out_features=1024, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=1024, out_features=4096, bias=True)
(fc2): Linear(in_features=4096, out_features=1024, bias=True)
(final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
(layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
)
)
(lm_head): Linear(in_features=1024, out_features=57525, bias=False)
)
)