Comments (3)
@CodLiver Are all your images have same dimensions as mentioned 400x544?
from pytorch-0.4-yolov3.
@CodLiver no, all are different. one is 424x544. The other is 1024x544 etc. The height is same, but width is different. It might be just matrix calc error which is fine. However, just gave for the heads up. The rest of the images are working fine. (w,h) form
from pytorch-0.4-yolov3.
You should check the image mode.
You can convert the image type by the following statements.
Image.open(image_path).convert('RGBA')
or
if image.mode != 'RGBA':
image = image.convert('RGBA')
from pytorch-0.4-yolov3.
Related Issues (20)
- I have issues in training ( evaluation problem! ) HOT 3
- data file not found in such condition HOT 5
- Why just output "Training for (12801,1285)"?? HOT 1
- Where should I edit code to change input image? HOT 3
- Can you tell me meaning of loss values? HOT 6
- find loss each epochs HOT 2
- What is 'eps' in evalutation? HOT 2
- Where can i find mAP in code? HOT 2
- training with single image HOT 1
- the part of subdivisions implemented HOT 1
- About def get_different_scale(self) and RuntimeError: .....size of tensor must match HOT 3
- loss HOT 1
- subdivisions HOT 1
- train issue HOT 1
- how to set maximum epoch on this code ? HOT 6
- How to test the images after training complete? HOT 1
- RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 608 and 416 in dimension 2 at /pytorch/aten/src/TH/generic/THTensor.cpp:689 HOT 1
- Training with multiple bounding boxes in a single image HOT 1
- training metrics HOT 1
- f
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 pytorch-0.4-yolov3.