Comments (5)
Hi, there. The thing is, you may not have those optical flow images as I have.
As I wrote in here, if the code couldn't find the optical flow images, the program will stop and exit. So that is why no progress.
I suggest you change the setting files, e.g., train_flow_split1.txt according to your situation. Usually due to different video codec, we may have different number of RGB or optical flow images.
from two-stream-pytorch.
Thanks so much for your fast reply. Get it.
from two-stream-pytorch.
Hello, I add the data files but it reports below errors, do you have any suggestions?
python main_single_gpu.py datasets/ucfnew
2017-09-24 08:46:46,667 - INFO - Building model ...
2017-09-24 08:47:05,368 - INFO - Model rgb_vgg16 is loaded.
2017-09-24 08:47:05,369 - INFO - Saving everything to directory ./checkpoints.
2017-09-24 08:47:05,369 - INFO - reach here
2017-09-24 08:47:05,494 - INFO - 13320 samples found, 9537 train samples and 3783 test samples.
2017-09-24 08:47:05,494 - INFO - 0.005
2017-09-24 08:47:05,495 - INFO - reach here
Traceback (most recent call last):
File "main_single_gpu.py", line 368, in
main()
File "main_single_gpu.py", line 190, in main
train(train_loader, model, criterion, optimizer, epoch)
File "main_single_gpu.py", line 232, in train
for i, (input, target) in enumerate(train_loader):
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 201, in next
return self._process_next_batch(batch)
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 221, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 40, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 109, in default_collate
return [default_collate(samples) for samples in transposed]
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 109, in
return [default_collate(samples) for samples in transposed]
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 89, in default_collate
storage = batch[0].storage()._new_shared(numel)
File "/home/ytan/miniconda3/lib/python3.6/site-packages/torch/storage.py", line 113, in _new_shared
return cls._new_using_fd(size)
RuntimeError: unable to write to file </torch_25231_36990222> at /opt/conda/conda-bld/pytorch_1503970438496/work/torch/lib/TH/THAllocator.c:271
from two-stream-pytorch.
Sorry, I don't know why such error occurs. I think it maybe due to different version of python or pytorch. I am modifying my code right now to achieve good accuracy on flow stream. I will test on different versions of pytorch to see if I can reproduce your errors.
from two-stream-pytorch.
from two-stream-pytorch.
Related Issues (20)
- About pre-trained Model HOT 2
- test video HOT 5
- Question about training the models together HOT 2
- Different running env? HOT 5
- Can you provide your results for loss and accuracy values of spatial and temporal training?
- The number of GPUs? HOT 1
- I use your restnet152 model parameters for testing, but in split_1 the accuracy is only 67.59%.
- Use the video input from the camera for action recognition HOT 7
- Problems about VideoSpatialPrediction.py HOT 2
- How is the two streams fused ? HOT 1
- What is the accuracy of UCF101?
- what's version of pytorch and cuda
- dense_flow 可不可以在windows安装 HOT 1
- 如果没有安装dense_flow,运行build_of.py文件,是不是不会运行出结果 HOT 1
- fusion two stream feature?
- a PROBLEM when using VGG as motion model
- 老师我想问下怎么late fusion呀 HOT 1
- 关于抽帧的图片存放路径 HOT 2
- video sampling rate in training two-stream network
- About parameter --new_length in training RGB videos
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from two-stream-pytorch.