Gavin-zsr

Img width not adpat to the parent div

3

When the `img `rendered in the `div`, its size doesn't adapt to the parent `div's `width, if this img over the div's width, it will exceed the div. And setting...

关于数据集标注问题

1

是否需要在json标注文件中提供角度的信息，例如 ``` 'images': [ { 'file_name': 'COCO_val2014_000000001268.jpg', 'height': 427, 'width': 640, 'id': 1268 }, ... ], 'annotations': [ { 'segmentation': [[192.81, 247.09, ... 219.03, 249.06]], # if you have mask...

Hi, thank you for sharing such a great code! Could you please provide a example about how to make own annotation files and the structure of data directory. Thanks a...

我使用自己的数据集训练，图片大小为224*224，全连接层参数为 `self.classifier = nn.Sequential( nn.Linear(512 * 7 * 7, 4096), nn.ReLU(True), nn.Dropout(), nn.Linear(4096, 4096), nn.ReLU(True), nn.Dropout(), nn.Linear(4096, num_classes), )` 剪枝前能够正常跑通网络，剪枝后就出现尺寸不匹配问题 `RuntimeError: size mismatch, m1: [32 x 12544], m2: [24832 x...

In roi_box_predictors.py, I didn't find the code of conv_head layers, it seems that there is only fc_head layer. Can you tell me where I can find these two heads code....

多GPU训练

1

请问代码需要哪些修改才能使模型使用多卡训练呢？ 我在train.py文件中直接加入了 `device = "cuda:0" if args.cuda: model = model.cuda(device) model = torch.nn.DataParallel(model, device_ids=[0,1,2])` 但是在模型验证时报错 Traceback (most recent call last): File "train.py", line 538, in main(parser.parse_args()) File "train.py", line 512,...