Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

train error #3

Open
davidqing2000 opened this issue May 6, 2020 · 1 comment
Open

train error #3

davidqing2000 opened this issue May 6, 2020 · 1 comment

Comments

@davidqing2000
Copy link

File "D:\BaiduNetdiskDownload\yolo4_tensorflow2-master\src\yolo4\util.py", line 113, in yolo4_loss
input_shape = tf.cast(tf.shape(yolo_outputs[0])[1:3] * 32, tf.dtype(y_true[0]))
IndexError: list index out of range

似乎以上错误的产生源自以下, 当len(anchors)小于3时,num_layers 则为0了,yolo_outputs 的LIST为空。
num_layers = len(anchors) // 3 # default setting
yolo_outputs = args[:num_layers]

怎么去修复?另外是否有TEST.PY提供?

@YH-Kong
Copy link

YH-Kong commented May 18, 2020

在sources/dataSet中找到kMeansAnchor.py,修改里cluster_number 使其大于3(数据集不够的话,需要自己添加),运行它之后再重新训练

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants