Issues
- 1
datasets used in model training
#265 opened by paden118 - 1
AssertionError when I inference
#267 opened by z369437558 - 2
- 1
ABOUT ucf101_json
#274 opened by theones-g - 0
how to change the number of clips generated arround the selected temporal position ?
#282 opened by sebyo - 0
How to calculate UCF101's top1 video level accuracy
#270 opened by YTHmamba - 1
transforms.Scale renamed transforms.Resize
#278 opened by mashakhart - 4
How big CPU/GPU memory need to run 3D ResNext-101
#231 opened by lily2lab - 0
error : expected tensor as element 0 in argument 0
#281 opened by sebyo - 0
evaluate top-1 video accuracy of recognition result : invalid argument for the ground truth ?
#280 opened by sebyo - 2
KeyError: 'Biking' when training on UCF101
#238 opened by N00k0428 - 2
what does the code line: "r3d200_KM_200ep.pth: --model resnet --model_depth 200 --n_pretrain_classes 1039" mean ?
#277 opened by wuchengyu123 - 2
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
#276 opened by shizishen - 2
- 0
is there 3d densenet pretrained models?
#273 opened by emergencyd - 1
Image Resolution 112*112
#272 opened by darshvirbelandis - 3
train on ucf,"ValueError: num_samples should be a positive integer value, but got num_samples=0"
#240 opened by N00k0428 - 0
Why is opt.n_val_samples 3
#271 opened by YTHmamba - 4
unable to create val.json
#249 opened by suravijayjilla - 2
Running on Windows, convert avi to jpg. FileNotFoundError: [WinError 2] The system cannot find the specified file.
#269 opened by YTHmamba - 4
Running on Windows, convert avi to jpg. FileNotFoundError: [WinError 2] The system cannot find the specified file.
#241 opened by N00k0428 - 0
- 0
- 4
- 0
pretrained model on IG-65M or IG-65M+Kinetics
#264 opened by paden118 - 1
Accimage is not available
#263 opened by huanggeng698 - 0
Accuracy for ntu60 RGB
#262 opened by dhruvgrover1251 - 0
ResNeXt101-kinetics on HMDB51-split02,split-03; and UCF101-split02,split03 pretrained model
#261 opened by lurchycc - 1
questions about old pretrained models
#250 opened by qzhb - 2
Error when load state_dict to finetune on ucf101 from pretrained model r2p1d34_K_200ep.pth : Missing key(s) in state_dict
#256 opened by nl8590687 - 0
training from scratch
#259 opened by Tortoise17 - 0
Question About Batch_size and Epoch
#260 opened by EmirhanToprak - 0
input_shape
#258 opened by MoGomaa - 0
module.***
#257 opened by WhitePageWu - 0
Data Augmentation Question
#255 opened by EmirhanToprak - 0
Bug in TemporalEvenCrop
#254 opened by ombretta - 2
Slow dataloading every N batches, where N=num_threads
#252 opened by exnx - 1
use model test single video
#253 opened by 784682065 - 0
Test model
#251 opened by harddrad - 2
Is there a simple way to get inference results on video files that are not part of the considered data sets?
#237 opened by quenot - 1
visualization!!!
#246 opened by slighting666 - 0
Training for new videos.
#248 opened by suravijayjilla - 2
- 2
KeyError of distributed training
#244 opened by byrsongyuxin - 1
GPU utilization rate and distribution training
#245 opened by byrsongyuxin - 1
error in generating ucf101.json
#239 opened by N00k0428 - 1
Very poor performance on pre-trained models.. maybe un matching Labels to index file
#243 opened by Purav-Zumkhawala - 1
Train time on UFC101 fine tuning on fully connected layer and loading model query
#242 opened by Purav-Zumkhawala - 1
avi failed to generate jpg
#236 opened by N00k0428 - 0
I inflated the google's lasted lightweighted 2d cnn model: MobileNetv3 to 3d, and get a higher precision 52% on ucf101 from scratch
#234 opened by Huixxi