-
Namespace(annotation_path='/home/nichao/data/kinetics.json', arch='resnet-34', batch_size=128, begin_epoch=1, checkpoint=5, crop_position_in_test='c', dampening=0.9, dataset='kinetics', ft_begin_index…
-
I'm trying to fine tune ResNet-34 for UCF101 dataset with this command
python main.py --root_path ~/Downloads/data --video_path UCF101/UCF101_jpg --annotation_path UCF101/ucfTrainTestlist/ucf101_01…
-
Hi, thanks for sharing codes.
Two questions here:
1. I extracted video features by using this pre-trained model (resnet-34-kinetics-cpu.pth) and I checked the outputs that the dimension of extracted…
-
When I run train.py, there is a error:
"ImportError: cannot import name 'DetectMultiBackend' from 'models.common'."
In modles/common.py, class DetectMultiBackend is not found.
Looking forward to a …
-
I tried using wide_resnet_imagenet64_1000, but found that it is giving zero accuracy. So, wanted to double check if this usage is correct. Here I am evaluating its natural accuracy on: Imagenet64_val…
-
i train dlav0_34 on a single 1080ti gpu, found it cost 2 hours per epoch on coco-train-data, while resnet34 needs only 48 min, both with batch_size=16, is this normal ?
-
你好，关于resenet作为backbone，请问它是选取resnet多少（18,34,50）进行特征提取
-
I am grateful for your works first. I get some problems when I load pretrained model file to R(2+1)D model. I used this command:
```
python main.py --root_path ../ --video_path ucf101_videos/jpg --a…
-
I'd like to share the code of classification with modification of train.py and datasets/brains18.py
The code is based on JasperHG90's commented at #58
To deal with the issue of Classification, there…
-
Thank you for your excellent job about the dropblock. However, there are some errors when I run the code. It occured in the 34 line of resnet-cifar10.py, self.layer1 = self._make_layer(block, 64, …