ssd.pytorch
ssd.pytorch copied to clipboard
amdegroot
A PyTorch Implementation of Single Shot MultiBox Detector
@ayukat1016 [PyTorch1.5.0 support new-style autograd function](https://github.com/amdegroot/ssd.pytorch/issues/444#issuecomment-625560662) Try 👆 in #444 It works well with Pytorch1.7.0 _Originally posted by @Abonnen in https://github.com/amdegroot/ssd.pytorch/issues/508#issuecomment-722395912_
I have own datasets with labeled. How to train it?
And how can I ensure that my adjustments really work?
I train VOC dataset wit SSD 300, but loss is too high, why? I have modified the batchsize and learning rate. `iter 1680 || Loss: 1885.2950 || timer: 0.1291 sec....
I try to change this code to implement video object detecction. I find the test phase is slow. Then I visualize the time cost. I find nms is key reason....
File "train.py", line 1, in from data import * File "/data/rui/ssd.pytorch-master/data/__init__.py", line 1, in from .voc0712 import VOCDetection, VOCAnnotationTransform, VOC_CLASSES, VOC_ROOT File "/data/rui/ssd.pytorch-master/data/voc0712.py", line 13, in import cv2 File "/opt/conda/lib/python3.6/site-packages/cv2/__init__.py",...
Hi, thanks for sharing of your project, it's really a great job! These days, I wanted to change the nms method to soft-nms method, but somehow, I failed, and I...
when i use this code to train my own dataset, i found the loss_c is about 1~2 after 100000 iter. And the IOU is only 0.27. Dose anyone have the...
File "train.py", line 255, in train() File "train.py", line 165, in train images, targets = next(batch_iterator) File "/home/chenzw/anaconda3/envs/tensor3/lib/python3.5/site-packages/torch/utils/data/dataloader.py", line 271, in next raise StopIteration StopIteration
