jfzhang95/pytorch-video-recognition
PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
PythonMIT
Issues
- 10
I can't download pretrained model
#44 opened by anzheng13 - 0
- 9
Method to pre-process video to images
#60 opened by hongbo-miao - 35
Train from scratch
#50 opened by aoluming - 0
About problems with training
#75 opened by Wangdanchunbufuz - 0
特征提取问题
#73 opened by LuckyDenKy - 3
- 0
dataset
#72 opened by zhaozhao678 - 0
- 0
ValueError:high<=0
#69 opened by slliugit - 0
- 0
ucf101 split 1 dataset
#68 opened by Eunchan24 - 1
about splitting the dataset
#26 opened by ilovekj - 2
目录树问题
#63 opened by TongShuo-Demon - 0
- 0
- 0
- 1
- 0
Questions about train_params?
#61 opened by Taylor-X76 - 0
- 4
Where is the dataset?
#52 opened by Y1YU - 1
how to pre-processing data?
#36 opened by libb999 - 2
Questions about the pretrained model
#57 opened by Krystal0606 - 0
The Code is Wrong in many place!!!!
#59 opened by HBlade - 0
ValueError: could not broadcast input array from shape (1080,1440,3) into shape (128,171,3)
#58 opened by agelosk - 1
Dataset not loading
#43 opened by WENDGOUNDI - 2
The accuracy of C3D training from scartch is low
#32 opened by Fancy-sf - 0
Questions about VideoDataset
#56 opened by AI-Hello - 1
- 2
- 0
Some questions about inference.py
#54 opened by Zhangzhiwei1995 - 0
Some questions about the file dataset.py.
#53 opened by Y1YU - 2
size mismatch for fc8.bias: copying a param with shape torch.Size([487]) from checkpoint, the shape in current model is torch.Size([101])
#40 opened by SeventhBlue - 3
Pretraining dataset
#34 opened by liamhiley - 1
- 0
About the Features
#49 opened by qc98 - 0
- 3
- 3
KeyError: 'state_dict'
#45 opened by marsna - 3
Inference.py question for frame process
#42 opened by Magsun - 0
- 1
- 0
- 0
- 1
- 1
model request
#35 opened by miaoxiaodaiblack - 2
- 0
- 0
ResNet Network Structure is Not Correct???
#28 opened by zkqiu - 5
out of memory?
#27 opened by goforfar