Comments (7)
@ahkarami No, it does not support. However, you can solve the problem by using the DataParallel module, or you can spread modules over multiple GPUs by passing an additional argument to .cuda()
. For example, .cuda(1)
will place the tensors and modules on 2nd GPU. For this, you should edit here and here.
from pytorch-tutorial.
@ahkarami Sorry for late reply. You can prepare a JSON file in the same form as MSCOCO dataset and use the code in the tutorial. Another way is to implement your own DataSet class. See here for how to implement custom dataset in PyTorch.
from pytorch-tutorial.
Dear @yunjey,
Thank you very much for your response. Just as another question, would you please tell me that your nice Image Captioning code supports Multi-GPU training or not?
from pytorch-tutorial.
Dear @yunjey, Thank you very much for your time and useful response.
from pytorch-tutorial.
@ahkarami @yunjey hi guys i am new to this topic i need to train for a custom dataset can you pls elaborate the steps for training with custom datasets . These are the things i am having currently with me
1.10k img database of various objects and tags for each image
Thanks in advance
from pytorch-tutorial.
Dear @abhigoku10,
You can use image captioning codebase in pytorch instead of above code. Actually, as I remember, I haven't use above code for training on another data sets, but by using the mentioned code I have done that. However, as I have remembered, that was a semi-sophisticated work to create a json file like the used one for MS-COCO.
from pytorch-tutorial.
Dear @yunjey
I want to train the model on my dataset, but it seems that my json file works wrong, could you tell me how to preprocess a json file?
Thanks very much
from pytorch-tutorial.
Related Issues (20)
- Issues in running tensorboard tutorial HOT 1
- Initialize DecoderCNN in Image captioning
- Some problems occurred when I used model evaluation
- RuntimeError in Logistic Regression python file
- Using LSTM method in Python
- size mismatch for pretrained models HOT 2
- pytorch
- No Jupyter Notebooks. HOT 1
- About the learning method of neural_style_transfer
- Does anyone know the source code of channel calculation in pytorch?
- make ur repo cloneable and not editable by anyone.
- TypeError: conv2d(): argument 'input' (position 1) must be Tensor, not tuple HOT 1
- AttributeError: module 'torch.nn' has no attribute 'linear' HOT 2
- ValueError: num_samples should be a positive integer value, but got num_samples=0 HOT 1
- main.py failed HOT 2
- some question about the position of 'optimizer.zero_grad()' HOT 4
- Pytorch tutorial HOT 1
- How can I get a PDF version of the tutorial HOT 2
- Cuda is true why don`t use itοΌ
- GNN model
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch-tutorial.