import tensorflow as tf a = tf.random.shuffle(tf.range(5)) a
tf.sort(a, direction='DESCENDING')
# Returns the index tf.argsort (A, direction = ' DESCENDING ' )
idx = tf.argsort(a, direction='DESCENDING') tf.gather(a, idx)
idx = tf.argsort(a, direction='DESCENDING') tf.gather(a, idx)
a = tf.random.uniform([3, 3], maxval=10, dtype=tf.int32)
a
tf.sort(a)
tf.sort(a, direction='DESCENDING')
idx = tf.argsort(a)
idx
# Return to the previous two values RES = tf.math.top_k (A, 2 ) res
res.values
res.indices
prob = tf.constant([[0.1, 0.2, 0.7], [0.2, 0.7, 0.1]])
target = tf.constant([2, 0])
# Probability largest index on top K_b = tf.math.top_k (Prob, 3 ) .indices k_b
k_b = tf.transpose(k_b, [1, 0])
k_b
# Real value broadcast, and prod comparison target = tf.broadcast_to (target, [. 3, 2 ]) target
def accuracy(output, target, topk=(1, )): maxk = max(topk) batch_size = target.shape[0] pred = tf.math.top_k(output, maxk).indices pred = tf.transpose(pred, perm=[1, 0]) target_ = tf.broadcast_to(target, pred.shape) correct = tf.equal(pred, target_) res = [] for k in topk: correct_k = tf.cast(tf.reshape(correct[:k], [-1]), dtype=tf.float32) correct_k = tf.reduce_sum(correct_k) acc = float(correct_k / batch_size) res.append(acc) return res
# 10 samples 6 class Output = tf.random.normal ([10, 6 ]) # so that the combined probability of all samples. 1 Output = tf.math.softmax (Output, Axis =. 1 ) # 10 corresponding to the sample labeled target tf.random.uniform = ([10], = MAXVAL. 6, DTYPE = tf.int32) Print (F ' Prob: output.numpy {()} ' ) pred = tf.argmax(output, axis=1) print(f'pred: {pred.numpy()}') print(f'label: {target.numpy()}') acc = accuracy(output, target, topk=(1, 2, 3, 4, 5, 6)) print(f'top-1-6 acc: {acc}')