i4yyds

why would you want to add init to the output of the attention block ?

BUG! 当图片(.xml)中不包含任何 object 时！

1

当训练集中存在一张图片不包含任何目标时，Data文件夹下的Transfroms_utils.py代码在进行boxes[:, 0] /= width计算时，会报错IndexError: too many indices for array。 原因是 这张图片并没有真值图，即xml文件中无法找到bbox，所以报错。 现在的新数据集中，这类图片很常见，希望大神解决一下，谢谢！

load vgg weight error

3

RuntimeError: Error(s) in loading state_dict for ModuleList: Missing key(s) in state_dict: "0.weight", "0.bias", "2.weight", "2.bias", "5.weight", "5.bias", "7.weight", "7.bias", "10.weight", "10.bias", "12.weight", "12.bias", "14.weight", "14.bias", "17.weight", "17.bias", "19.weight", "19.bias", "21.weight",...

Communicate in Chinese！中文交流！

11

去他娘的英文！ 我对代码中的loss层有4个疑问，目前已经解决3个。分享一些自己的观点，一起交流！ 1. 为什么使用 offset ？ 2. 为什么对 w和h 开根号 ？ 3. 为什么使用 offset_tran ？ 4. 四个loss的含义 ？

Non-Maximum Suppression

1

Hello, is there any non-maximal suppression module in the code?

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,...

请问如何才能改变batchsize的大小呢？

High memory usage by jmx_exporter when connecting to Kafka

1

Hi, I'm using jmx_exporter to connect to Kafka, and I noticed that it is consuming a significant amount of memory, around 600MB. I'm wondering why it requires such a large...

Thank you for sharing! If I use the structure of VGG+ deconvolution, which layers should I add attention to? Do all 16 layers of VGG need to be added as...