Issues
- 2
报错求助magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, '<'.(困扰我很久了救救孩子吧))
#133 opened by wys2929 - 3
- 0
mean() received an invalid combination of arguments - got (Tensor, list, keepdim=bool), but expected one of: * (Tensor input) * (Tensor input, torch.dtype dtype) * (Tensor input, int dim, torch.dtype dtype, Tensor out) * (Tensor input, int dim, bool keepdim, torch.dtype dtype, Tensor out) * (Tensor input, int dim, bool keepdim, Tensor out)
#135 opened by zhangxiaoyuyu - 2
Can you provide us the pytorch code for topK consensus and attention weight pooling consensus?
#108 opened by malarsaravanan1991 - 3
f**k-est implementation
#134 opened by Ontheway361 - 3
- 2
请问经过模型后的输出是什么格式呢?
#121 opened by shaitaiyangmie - 4
size mismatch for weights and bias
#104 opened by gwyy-mh - 3
size mistmatch?
#100 opened by HiIcy - 0
Need pre-trained ActivityNet weights for Pytorch
#132 opened by ADstudyer - 0
- 4
training tsn on kinetic400 is ok, but validating is very low. do you test your model on the kinetics400 data set
#114 opened by LiuChaoXD - 2
cannot downgrade pytorch to solve mismatch
#109 opened by tiangarin - 1
RuntimeError: Legacy autograd function
#126 opened by nasaweimao - 1
- 1
Training the TSN model on custom dataset - couldn't implement as mentioned in paper
#130 opened by anuraganand1838 - 2
- 0
video live test?
#129 opened by Mkarami3 - 1
What should I do if I want to change the main structure of the network to InceptionV3?
#102 opened by kaifeng777 - 0
- 1
No module named 'mmaction.datasets.utils'
#120 opened by dandingol03 - 6
Issue about training Kinetics400
#87 opened by fuyukaiKUN - 0
The score of rgb and flow
#127 opened by zkyunqi - 2
getting 84% in ucf101 on split 1
#125 opened by dandingol03 - 0
RuntimeError: bool value of non-empty torch.cuda.ByteTensor objects is ambiguous
#124 opened by dandingol03 - 1
error about epoch print statement when i use the main.py to train with ucf101 dataset
#123 opened by dandingol03 - 1
- 0
- 0
Feature Extraction
#115 opened by destousok - 0
- 0
- 0
model not find
#111 opened by gtgtgt1117 - 0
- 3
how to create RGB <ucf101_rgb_val_list> ?
#105 opened by omeryasar - 2
- 1
- 0
problem about VGG module
#107 opened by pangweilun - 0
Did anyone reproduce TSN on ActivityNet v1.3? Or are there any pretrained models on ActivityNet v1.3 available?
#106 opened by raxxerwan - 2
If I set the batchsize to 16, which parameters should I change accordingly, thank you very much.
#96 opened by ZealACMer - 1
test_model.py IndexError: list index out of range
#101 opened by immaping - 0
how can i compute the speed
#99 opened by iamhoushiyou - 2
- 1
.npz flow score file of hmdb51 and ucf101?
#90 opened by ZealACMer - 1
about flow length
#94 opened by Racha1992 - 2
About data prepare
#93 opened by Racha1992 - 0
- 2
- 4
How to do modality fusion
#89 opened by yojayc - 1
issue about fushion tools/eval_scores.py ValueError: operands could not be broadcast
#88 opened by sucaohan - 0
Issue in test_models.py
#86 opened