問題タブ [ctc]
For questions regarding programming in ECMAScript (JavaScript/JS) and its various dialects/implementations (excluding ActionScript). Note JavaScript is NOT the same as Java! Please include all relevant tags on your question; e.g., [node.js], [jquery], [json], [reactjs], [angular], [ember.js], [vue.js], [typescript], [svelte], etc.
python - CTC の TF 実装がどのように機能するかを理解する
TensorFlow で CTC 実装がどのように機能するかを理解しようとしています。CTC 機能をテストするためだけに簡単な例を書きましたが、何らかの理由でinf、いくつかのターゲット/入力値を取得しています。
コード：
サンプル出力:
私はそこに何が欠けているのですか!?
keras - CTCBeamSearchDecoder thinks sequence_length of shape (2,) is not a vector
Trying to run a beam search in a Keras model, I get confusing (and conflicting?) error messages. My model has inputs such as
and the CTC loss function requires the [1] shapes in input and label length. As far as I understand, the output should be obtained with something like
but as-is, that leads to a complain about the shape of input_length
but if I chop off that dimension
the model definition runs, but when I run y = paths([x, numpy.array([[30], [30]])]) with a x.shape == (2, 30, 513) I suddenly get
What am I doing wrong?