top1 = 0.0
top5 = 0.0
class_probs = model.predict(x)
for i, l in enumerate(labels):
class_prob = class_probs[i]
top_values = (-class_prob).argsort()[:5]
if top_values[0] == l:
top1 += 1.0
if np.isin(np.array([l]), top_values):
top5 += 1.0
print("top1 acc", top1/len(labels))
print("top1 acc", top5/len(labels))
https://stackoverflow.com/questions/42327006/how-to-calcu...
How to calculate the complexity? How about the space?
How to calculate CLV（customer lifetime value）and predict ...
How to calculate bottleneck for timing inspection? Data P...
释义1. number to calculate how many people or things there ...
N voracious fish are moving along a river. Calculate how ...
Process CPU usage How to calculate the CPU usage of a pro...
Use info command in redis-cli or How to calculate the rat...
1.What is the accuracy of your decision tree? 2. How many...
题目描述：Given a sequence a[1..n], you need to calculate how ...
本文标题：How to calculate top5 accuracy?
本文链接：https://www.haomeiwen.com/subject/omoipqtx.html
网友评论