ssd.pytorch
ssd.pytorch copied to clipboard
amdegroot
A PyTorch Implementation of Single Shot MultiBox Detector
I was trying to perform MC Dropout sampling using this model as explained in [this research paper](https://arxiv.org/abs/1809.06006). I am attaching the screenshot of the method as described in the above...
How can I train VOC2007 but not VOC2012 
hello dear dose any one know why result of SSD Algorithm produced too many boxes on my video during inferences .I trained for 20000 iteration with 32 batch size and...
`loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))` I'm confused with this line of code. Why not using conf_data to select hard examples? What is this loss_c stand for?
I replaced the network among the codes in the Repo. (resnet101) Losses are decreasing normally. The results of running demo.py create too many boxes. Is it too early to judge...
Hello, I executed train.py with multiple GPUs (I setted with `CUDA_VISIBLE_DEVICES=0,1` because I got double GPUs), and I got error : ``` Traceback (most recent call last): File "train.py", line...
Hi, I've been working on a semi-supervised implementation and wanted to write pseudo-label code for this codebase. I thought the naive way of doing `criterion(out, model(out))` would have sufficed, but...
nvidia.line( NameError: name 'nvidia' is not defined
D:\ProgramData\Anaconda3\python.exe D:/code/python/ssd.pytorch/train.py Loading base network... Initializing weights... Loading the dataset... Training SSD on: VOC0712 Using the specified args: Namespace(basenet='vgg16_reducedfc.pth', batch_size=32, cuda=True, dataset='VOC', dataset_root='D:\\code\\python\\ssd.pytorch\\data/VOCdevkit/', gamma=0.1, lr=0.001, momentum=0.9, num_workers=4, resume=None, save_folder='weights/', start_iter=0,...
why the "mean" equals to(104/256.0, 117/256.0, 123/256.0)? Is there any according about it? Please.
