Comments (5)
Hiya,
- Yes, I think that the bigger the blob the easier for it to be separated, as networks often struggle with small resolutions.
- The scale in the global split loss is indeed the number of points.
- You are right that there is imbalance between positive and negative samples. It would be interesting to optimize the focal loss to handle that.
from lcfcn.
I read the paper again. the blob will be remove just retain the blob contains point .
the probs will drop down and can not form a blob. pretty good!
from lcfcn.
split_mode loss
if blob_dict["n_multi"] > 0:
loss += compute_split_loss(S_log, S, points, blob_dict)
# Global loss
S_npy = ut.t2n(S.squeeze())
points_npy = ut.t2n(points).squeeze()
for l in range(1, S.shape[1]):
points_class = (points_npy==l).astype(int)
if points_class.sum() == 0:
continue
T = watersplit(S_npy[l], points_class)
# imsave(batch["name"][0], T*255)
T = 1 - T
# print(batch["image_path"][0])
scale = float(counts.sum())
loss += float(scale) * F.nll_loss(S_log, torch.LongTensor(T).cuda()[None],
ignore_index=1, reduction='elementwise_mean')
what is the difference between the split loss and globa loss?
how the scale works?
it will narrow the blob?
please tell me!
from lcfcn.
Hi there!
- what is the difference between the split loss and global loss?
The global loss is just another variation of the split loss. There is a local split loss and a global split loss.
- The local split loss makes the model set the split boundaries that only separate between objects that are in the same blob as background.
- The global split loss makes the model set the split boundaries that separate all objects in the image as background.
- how the scale works?
The model automatically learns the scale. It will find the right scale that allows it to output one blob per object.
- it will narrow the blob?
Yes, without the split loss the model will output one big blob containing many objects. With the split loss, the model will output smaller blobs to make sure there is one blob per object.
from lcfcn.
yeah I figure out the the split loss.
the scale in local split loss is the num of pixs in blob. can I deem the bigger the blob is .the easier the blob will be separate? and the scale in global split loss is the num of the points.
my thoughts may not be mature enough. whether there is a problem between the ratio between positive samples and negative samples? the num of negative samples is bigger than positive samples.is helpful if use focal loss?
thanks for your detailed and fast explaination.
from lcfcn.
Related Issues (20)
- Reproducing results in paper
- Inference problem HOT 3
- The prediction was incorrect where use best_model_trancos_ResFCN.pth HOT 1
- How to annotate fro custom data training? HOT 4
- Where are the path_model and path_opt files when training from scratch? HOT 8
- Error in losses.py HOT 2
- ValueError: exp_list is empty... HOT 8
- Can you kindly provide the scripts for testing and visualization of blobs? HOT 2
- Error in loading .pth HOT 2
- Can you provide a model that you trained on trancos data?
- Display results HOT 1
- Wrong output with other backbone networks HOT 4
- How to use the multiclass version?How to organize the dataset?Pascal VOC for example... HOT 1
- How to create files for folder images?
- Inference script HOT 2
- Batch-aware loss function? HOT 3
- How to plot loss during the training ?
- Dear author, can you give me a test.py HOT 1
- sorry,I am a green hand HOT 1
- ERROR: Command errored out with exit status 128 HOT 4
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 lcfcn.