Dive into Data Science

www.dlology.com/blog/how-to-use-return_state-or-return_sequences-in-keras/ How to use return_state or return_sequences in Keras | DLology Posted by: Chengwei 2 years, 9 months ago (Comments) You may have noticed in several Keras recurrent layers, there are two parameters, return_state ,and return_sequences. In this post, I am going to show you what they mean and when to use them in real www.dlol..

eehoeskrap.tistory.com/293 [TensorFlow] Anaconda 가상환경 이용하여 TensorFlow GPU 설치 아나콘다 설치 후 1. 가상환경 생성 conda create -n 가상환경이름 python=3.6 2. 가상환경 Activation source activate 가상환경이름 3. TensorFlow GPU 설치 conda install -c anaconda tensorflow-gpu (2019년.. eehoeskrap.tistory.com laondev12.tistory.com/13

tf.nn.softmax_cross_entropy_with_logits_v2 가 수행하는 3가지 연산 logits인 (y_hat)에 softmax 함수 적용 (정규화를 위해) : y_hat_softmax = softmax(y_hat) cross-entropy loss 계산 : y_cross = y_true * tf.log(y_hat_softmax) 각 데이터로부터 각각 loss 값 계산 : -tf.reduce_sum(y_cross, reduction_indices=[1]) 아래의 코드는 이것을 완벽하게 보여준다. 코드 : y_true = tf.convert_to_tensor(np.array([[0.0, 1.0, 0.0],[0.0, 0.0, 1.0]])) y_hat = tf.convert_to_tensor..