herrickli

Error when reload weights

5

If I interrupt the process of training, I can not reload the weight `ssd300_voc_10000.pth` which is the weight trained and saved in `weights/`, the error information is as follows. ```...

请问只要改变了类别数量就一定不能加载预训练模型吗，我把类别改为五类，加载他原来的预训练模型最后效果很差，不知道是不是这个原因．

1

请问只要改变了类别数量就一定不能加载预训练模型吗，我把类别改为五类，加载他原来的预训练模型最后效果很差，不知道是不是这个原因． 谢谢～

dataloader报错

1

您好，在使用Faster RCNN模型的时候当batch size>1时，在dataloader文件中报错，提示数据尺寸不一致，我的数据原本尺寸是不相等的。请问要Faster RCNN是不支持batch size>1吗，或者要怎么解决呢。谢谢~ ``` File "detection_template/dataloader/dataloaders.py", line 51, in collate_fn target['image'] = torch.stack([sample['image'] for sample in batch]) RuntimeError: stack expects each tensor to be equal size, but got...

Hi, I meet some problem using your code. If I use 101 depth of SSDRES512, the output channel number of conv3 is 64, and after some Bottlenecks, the output channel...

How to save the model into pb model

2

Hi, I want to save the model into pb model, some information from Internet says I need to use the output node to save it, but it hard to find...