-
## 📚 Documentation
Please describe what kind of files should be in annotation_path, and what the files should contain. It is not obvious.
cc @pmeier
-
I am conducting experiments on UCF-101. When referring to [datasets/ucf101.py](https://github.com/kenshohara/3D-ResNets-PyTorch/blob/master/datasets/ucf101.py), I didn't found any arguments to support…
-
Hi @hx173149 @gudongfeng @chuckcho @cc786537662
File "/home/ltroot/data1/C3D-tensorflow-master/train_c3d_ucf101.py", line 171, in run_training
varlist1 = list(set(weights.values() + biases.…
-
@gulvarol
Hi, I want to compute optical flow for UCF101 datasets. Do you remember how long it takes? Thanks for your help.
-
Hi， how did you get the result of Middlebury dataset? I have got the same results of your pertrained model on Vimeo90K and UCF101 datasets, but got a poor result on Middlebury. Could you please provid…
-
**Short description**
when I try to use the UCF101 dataset ，the program report something like this
tensorflow.python.framework.errors_impl.OutOfRangeError: E:\tfdsdata\datasets\ucf\downloads\thumos1…
-
The reported accuracies on the oxfordpets and ucf101 datasets are 85.83 and 62.70, respectively, but our reproduced accuracies are only 82.91 and 61.19. How can I improve the accuracy?
Here is my env…
-
Hi Feichtenhofer
I have the following version incompatibity problem as follow:
replace classifier layer of fc1000_bias
No public property dilate exists for class dagnn.Conv.
I use the matcon…
-
@kenshohara
Hi
Thank you for sharing your code.
I just run the code for UCF101 dataset. Is there any function that plots the results over epoch for train and validation set?
-
Upon reviewing the reference_ucf101.py, I observed that the UCF-101 models showcased subpar performance on the UCF-101 dataset, particularly when applying varied data augmentation techniques. Further …