例如，我有這個(gè)張量：Boxes(tensor([[ 138.7087, 670.4597, 194.0305, 788.7614], [1744.7915, 597.5836, 1790.3419, 709.9775], [ 384.6486, 526.4615, 428.3247, 622.8542], [1396.4264, 562.2295, 1444.1472, 653.7578], [1135.2161, 504.2900, 1169.5103, 608.7569], [1035.7961, 771.2336, 1100.9679, 919.1385], [ 696.5236, 419.2245, 738.7255, 503.7422], [ 63.7905, 362.0703, 93.2846, 439.7708], [ 834.4216, 591.6379, 880.6455, 690.0402], [1003.2484, 612.4662, 1055.1136, 704.1541], [ 852.7735, 330.7743, 879.5329, 396.9597], [ 840.9529, 526.4127, 871.9255, 594.8165], [ 798.7436, 520.0127, 834.4247, 601.9252], [1539.8649, 600.5634, 1576.6362, 679.7695], [ 151.1197, 366.5715, 186.4236, 434.6742], [ 152.5436, 322.7310, 196.8471, 429.3589], [ 164.2602, 322.5941, 195.3645, 386.3824]], device='cuda:0'))我想獲取每行的所有 for 值并將其寫入不同的變量，這怎么可能？
3 回答
largeQ
TA貢獻(xiàn)2039條經(jīng)驗(yàn) 獲得超8個(gè)贊
import tensorflow as tf
a = tf.convert_to_tensor([
[ 138.7087, 670.4597, 194.0305, 788.7614],
[1744.7915, 597.5836, 1790.3419, 709.9775],
[ 384.6486, 526.4615, 428.3247, 622.8542],
...
[ 152.5436, 322.7310, 196.8471, 429.3589],
[ 164.2602, 322.5941, 195.3645, 386.3824]
])
b = tf.unstack(a, axis=0)
慕村225694
TA貢獻(xiàn)1880條經(jīng)驗(yàn) 獲得超4個(gè)贊
假設(shè)t是你的張量對(duì)象。
ax1 = t.shape[1]
for i in range(ax1):
vals = t[:,i]
# do stuff
白衣非少年
TA貢獻(xiàn)1155條經(jīng)驗(yàn) 獲得超0個(gè)贊
用于tf.split()獲取張量列表（每行一個(gè)）：
boxes = tf.constant([[ 138.7087, 670.4597, 194.0305, 788.7614],
[1744.7915, 597.5836, 1790.3419, 709.9775],
[ 384.6486, 526.4615, 428.3247, 622.8542],
[1396.4264, 562.2295, 1444.1472, 653.7578],
[1135.2161, 504.2900, 1169.5103, 608.7569],
[1035.7961, 771.2336, 1100.9679, 919.1385]],)
tf.split(boxes, num_or_size_splits=boxes.shape[0], axis = 0)
[<tf.Tensor: shape=(1, 4), dtype=float32, numpy=array([[138.7087, 670.4597, 194.0305, 788.7614]], dtype=float32)>,
<tf.Tensor: shape=(1, 4), dtype=float32, numpy=array([[1744.7915, 597.5836, 1790.3419, 709.9775]], dtype=float32)>,
<tf.Tensor: shape=(1, 4), dtype=float32, numpy=array([[384.6486, 526.4615, 428.3247, 622.8542]], dtype=float32)>,
<tf.Tensor: shape=(1, 4), dtype=float32, numpy=array([[1396.4264, 562.2295, 1444.1472, 653.7578]], dtype=float32)>,
<tf.Tensor: shape=(1, 4), dtype=float32, numpy=array([[1135.2161, 504.29 , 1169.5103, 608.7569]], dtype=float32)>,
<tf.Tensor: shape=(1, 4), dtype=float32, numpy=array([[1035.7961, 771.2336, 1100.9679, 919.1385]], dtype=float32)>]
添加回答
舉報(bào)
0/150
提交
取消