-
hello, I got following error:
Expected input number 1, A, to be nonempty.
Error in imresize>parsePreMethodArgs (line 333)
validateattributes(A, {'numeric', 'logical'}, {'nonsparse', 'nonempty'}, mf…
-
if I want to fine tune the pre-trained model on UCF101, how could I get the performance of 96.8%?
In my settings, fine-tuning was only performed to train layer4 and the fully connected layer, and the…
-
Does anyone train tsm on ucf101 only using imagenet pretrained resnet50? No Kinetics pretrained.
I train tsm on ucf101 only using RGB stream, imagenet pretrained resnet50, with hyper-parameters sam…
-
Does anyone have any idea for this problem? Please help me out. I am using tensorflow 1.7.0 and numpy 1.14.5.
Traceback (most recent call last):
File "predict_c3d_ucf101.py", line 155, in
tf…
-
Hi anyone met this error? Anyone know how to solve this?
(base) james@james-MS-7C00:~/tsn-pytorch$ python main.py ucf101 RGB ucf101_rgb_train_list ucf101_rgb_val_list --arch BNInception --num_se…
-
Thank you for sharing. Regarding the current work, I have some questions I hope you can answer.
①How to deal with the data sets of UCF101 and HMDB51? What is the sampling frame rate when the video i…
-
According to the code, there are 2 folders inside the "UCF101/tvl1_flow/" directory, "u" and "v".
When we download the zip file from [this](https://github.com/feichtenhofer/twostreamfusion) mentioned…
-
Hi there.
I've finished to download UCF101-dataset. But, I don't know how to divide this data set between train and test and how image files to put in where.
Also, I cannot understand about class_…
-
I have a pertained model and I want to test it with the data that I have. But I don't know how to manipulate data to feed the network. Can you tell me what should I do? Thanks
-
Can anyone share the .npz flow score file of hmdb51 and ucf101 for TSN. Thank you very much.