NLDF

NLDF copied to clipboard

请问PR曲线是用python 的代码运行的，能否提供下评测PR曲线的代码

1

请问PR曲线是用python 的代码运行的，能否提供下评测PR曲线的代码

StormArcher

loss变为NAN

10

您好！我将您代码中的网络结构简化为以下代码： self.pool5_conv1 = self.Conv_2d(vgg.pool5, [3, 3, 512, 128], 0.01, padding='SAME', name='c1_') self.contrast_1 = self.Contrast_Layer(self.pool5_conv1, 3) self.pool5_conv2 = self.Conv_2d(tf.concat([self.pool5_conv1, self.contrast_1], axis=3), [3, 3, 256, 256], 0.01, padding='SAME', name='c2_') self.pool5_conv3 = self.Conv_2d(self.pool5_conv2,...

i4yyds

作者您好，能提供一下运行环境嘛？这边调试总出错，谢谢

1

GewelsJI

loss函数实现是不是有问题？稍微复杂的图片loss就直接nan了

2

zhanpx

Crash while training

3

Hi, I'm trying to train my own model according to your implementation. Since I encounter some gradient error cause Nan or Inf error. Below is the log when training crash...

shouyinz

AttributeError: 'Model' object has no attribute 'keep_prob'

1

I met the following error: Traceback (most recent call last): File "TestingModel.py", line 75, in model.keep_prob: 1}) AttributeError: 'Model' object has no attribute 'keep_prob' How can I fix it?

ShuhanChen