Skip to content

S
seminar-breakout
Commit c8d409a6 authored by Yuxin Wu's avatar Yuxin Wu
Browse files
Options

notes about superresolution (#706)

parent 45ebac95
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
examples/README.md
View file @ c8d409a6
......@@ -27,7 +27,7 @@ These examples don't have meaningful performance numbers. They are supposed to b
| [Spatial Transformer Networks on MNIST addition](SpatialTransformer) | reproduce paper |
| [Visualize CNN saliency maps](Saliency) | visually reproduce |
| [Similarity learning on MNIST](SimilarityLearning) | |
| Single-image super-resolution using [EnhanceNet](SuperResolution) | visually reproduce |
| Single-image super-resolution using [EnhanceNet](SuperResolution) | |
| Learn steering filters with [Dynamic Filter Networks](DynamicFilterNetwork) | visually reproduce |
| Load a pre-trained [AlexNet, VGG, or Convolutional Pose Machines](CaffeModels) | |
......
examples/SuperResolution/README.md
View file @ c8d409a6
......@@ -33,7 +33,8 @@ python data_sampler.py --lmdb train2017.lmdb --input train2017.zip --create
python enet-pat.py --vgg19 /path/to/vgg19.npz --data train2017.lmdb
```
Training is highly unstable and does not often give results as good as the pretrained model.
Training is highly unstable and does not often give good results.
The pretrained model may also fail on different types of images.
You can download and play with the pretrained model [here](http://models.tensorpack.com/SuperResolution/).
3. Inference on an image and output in current directory:
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment