Comments (3)
Sorry. Found our mistake. We forgot to pass the pre_trained models path. Otherwise it would initialize weights randomly and use it to generate images, which makes sense.
The command should be:
python runtime.py --inference --split 2 --pre_trained_disc checkpoints/disc_190.pth --pre_trained_gen checkpoints/gen_190.pth
After this, I got really good images:
a cluster of flowers with white petals and no visible pistils
a flower large multiple layered slender petals of bright yellow with a short stamen.?
a flower with bright, tall, orange pointed petals and dark forest green pedicel.?
Looks cool. Thanks author. Awesome work :) Now, we will try to implement the same on birds and COCO dataset as well as try using WGAN.
Similarly on birds data set, it would be
python runtime.py --inference --pre_trained_disc checkpoints/birds/disc_190.pth --pre_trained_gen checkpoints/birds/gen_190.pth --save_path birds --dataset birds --split 2
from text-to-image-synthesis.
Yup, I also got the same exact result for trying it out on the test data using the above command. And the image looks like that only. I hope that author helps us with some direction to resolve this.
I am guessing that may be the command we used to run the test inference is long. Can the author please suggest the right command.
from text-to-image-synthesis.
@sriharsha-sammeta Thanks for answering.
from text-to-image-synthesis.
Related Issues (20)
- Release models for Flowers, Birds and COCO datasets HOT 8
- Loss function
- torch model
- cannot identify image file <_io.BytesIO object at 0x7f2d80b2e770> HOT 5
- inception scores? HOT 1
- Can you run this without nvidia? HOT 1
- Duplicate embeddings in convert_cub_to_hd5_script.py HOT 1
- Mapping to dataset folders. HOT 4
- How long do I need to train? HOT 1
- What is the file of text embeddings? HOT 2
- text embeddings preparation HOT 1
- batch image generation HOT 1
- A question about text and image encoding HOT 1
- How to add embedding path?
- How to pass the text as input to the generator model and generate images? HOT 1
- Can't Use flowers.hdf5 HOT 1
- Error on visualize.py HOT 1
- trainer.py RuntimeError: size mismatch (got input: [2], target: [64]) HOT 2
- TypeError: a bytes-like object is required, not 'str' in "Text2ImageDataset.py"
- Cannot download HDF5 file HOT 1
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 text-to-image-synthesis.