PytorchSSD

PytorchSSD copied to clipboard

just ran into this import error while trying to run train_test.py.... how can i solve it?

Gabriel-Arredondo

想问下大家，在训练的过程中又碰到AP为0的情况吗，我是用的自己的数据集训练的。num_class啥的都改过了，实在不知道该咋办了

1

YXB-NKU

The mAP of SSD-Resnet is lower than SSD-VGG16.

1

Thanks for your work ! I just replace the backbone of **SSD** with 'torchvision.models.resnet', but the mAP becomes lower than the VGG-16. The results are follow: | backbone | mAP...

Taotaoxu

Unexpected key(s) in state_dict: L2Norm.weight

2

Hi, I tried to using FSSD in live.py by adding the following code: ``` elif args.version == 'FSSD_vgg': from models.FSSD_vgg import build_net ``` And I have downloaded the pretrained model...

linhl97

Loss does not decrease for coco

3

Have you ever trained on coco for these models? I try to train coco with original SSD. However, the loss keeps increasing especially for the localization loss from 3 to...

strongwolf

运行train_test.py时AssertionError: Invalid device id

2

Traceback (most recent call last): File "train_test.py", line 183, in net = torch.nn.DataParallel(net, device_ids=list(range(args.ngpu))) File "/home/cv2018/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 102, in __init__ _check_balance(self.device_ids) File "/home/cv2018/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 17, in _check_balance dev_props = [torch.cuda.get_device_properties(i)...

Eileen2014

fssd divergent

1

``` Training FSSD_vgg on VOC0712 Epoch:1 || epochiter: 0/313|| Totel iter 0 || L: 0.3828 C: 1.9178||Batch time: 6.2867 sec. ||LR: 0.00400000 Epoch:1 || epochiter: 10/313|| Totel iter 10 ||...

lucasjinreal

[Errno 111] Connection refused

22

Hi, I am getting this error RuntimeError: The shape of the mask [8, 32756] at index 0 does not match the shape of the indexed tensor [262048, 1] at index...

nagitam

When run test( )

ZhangAdjy

from yacs.config import CfgNode as CN

johsnows