Comments (2)
I'm not affiliated with the authors, but I did run their training code and plot the loss curve. I also did a training run that started with their pretrained model. Both are for the "PixelLink + VGG16 2s" model.
Here is what I got when training from scratch.
The loss was still decreasing when I stopped it, but was at about 0.76.
Some caveats:
Deng et al. trained with 3 GPUs, 24 images/GPU, for 72 images/batch. To my understanding, the batch size is equivalent to one "step" in the code, also called one "iteration" in the paper. I trained with 1 GPU and 4 images/GPU, for a batch/step/interation size of 4 images. I only trained with a learning rate of 1e-3 (The authors did initial training with LR=1e-3 then changed to LR=1e-2. The loss blew up when I tried that. It might have just had a poor initialization.)
Here is what I got when loading the pretrained model, then training further.
The curve is noisy because I only ran it for a short while, so each marker on the plot represents an average of many fewer steps than in the plot above.
Note that:
Training starts at 73108 steps (the number of training steps in the pretrained model), for the authors' step size of 72 images/batch.
Here I used LR=1e-2, which was simply because I forgot to change it to 1e-3.
The curve is noisy in part because I only trained for a short while, so each marker in the plot represents the average of many fewer steps (and samples) than in the plot above.
The loss continues to decrease. This may be due to over-fitting. The model is large, the training set relatively small, and we are observing losses from the training set, not the test set.
from pixel_link.
@dengdan, I suggest closing this.
from pixel_link.
Related Issues (20)
- Why can't draw box in window 10 ?
- can not git this project HOT 1
- Two lines text
- tensorflow conversion to 2.0
- ValueError: Can't load save_path when it is None. HOT 2
- Question in pixel_link.py about the function 'cal_gt_for_single_image()'
- AttributeError: 'NoneType' object has no attribute 'startswith' HOT 2
- ValueError: Can't load save_path when it is None. HOT 2
- TypeError: Can not convert a list into a Tensor or Operation. HOT 1
- ./scripts/train.sh: 权限不够是怎么回事啊求帮助 HOT 1
- Where is base training model? HOT 1
- Invalid Syntax on util HOT 1
- Can I build this code successfully with tensorflow version 1.4? If anyone can do this, please let me know. Thank you so much!
- InternalError (see above for traceback): Blas SGEMM launch failed : m=61440, n=2, k=256
- After many steps the loss becomes NaN. (loss = Nan) HOT 2
- util HOT 3
- Testing on any image (Question) HOT 1
- Problem when restoring the trained model : FailedPreconditionError :Attempting to use uninitialized value count_warning
- loss = 0.0000
- win10 下可以用吗?怎么用
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 pixel_link.