lihuikenny
lihuikenny
AttributeError: 'model' object has no attribute 'centroids'
自己本地调试没有问题，提交集群训练的时候，会报这样的错误，但是找了很久没有找到问题。是代码中有某个地方用到了git，导致我上传集群git的过程中因为网络问题导致的错误？ 1、预训练模型是离线加载的，没有问题 2、环境都是离线安装的。 想请教一下，代码中是否有哪个地方用到了git这个操作？谢谢
thirdparty/mmdetection-2.17.0/mmdet/models/roi_heads/test_mixins.py", line 89, in simple_test_bboxes bbox_results = self._bbox_forward(x, rois) TypeError: _bbox_forward() missing 1 required positional argument: 'rois' 怎么样快速修复这个问题呢？谢谢
There is such an error when training your own data set, but there is no problem in checking my own data： Traceback (most recent call last): File "train.py", line 292,...
I want to use small or tiny model to train myself datasets because of GPU memory is too small. but I do not how to modify configs. I do not...
PostProcess中forward函数感觉是可以已batch的形式进行后处理，跟我的理解和调试，发现函数的返回结果，并不是已batch的形式返回的。简单说，就是我推理2张图像，假设输入 的size = (2, 3, 800,800), 按我的理解PostProcess返回应该是batch的形式，比如返回的box应该是的size应该是：[2,300,4]，2是batch,300是选择的数量，配置文件中设置了300, 4是box的维度。 target_sizes: tensor of dimension [batch_size x 2] containing the size of each images of the batch For evaluation, this must be the...
weight_CV: tensor([[[nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan, ..., nan, nan, nan], ..., [nan, nan, nan, ..., nan, nan, nan],...
Hi, 1. Would you like to provide the CAISA SURF dataset and private dataset, I am currently trying to repeat your work. If yes, you might send the dateset to...
It is recommended to add code to determine whether it is a gray image