Comments (2)
Hi! This is a good question, and sorry for not coming back to you sooner.
To me is looks like the net is reinitialised fine, but I can see that you use the same set of callbacks for every iteration. I don't know what you callback
contains, but I assume it might be an EarlyStopping
object. If this is the case, you need to reinitialise this too, meaning you end up with something like this
for lr in [0.01, 0.1, 0.001]:
net = tt.practical.MLPVanilla(in_features, num_nodes, out_features, batch_norm,
dropout, output_bias=output_bias)
model = CoxPH(net, tt.optim.Adam)
model.optimizer.set_lr(0.01)
callbacks = [tt.callbacks.EarlyStopping()]
log = model.fit(x_train, y_train, batch_size, epochs, callbacks, verbose=True,
val_data=val, val_batch_size=batch_size)
Does this solve the issue?
from pycox.
Yes, it works for the issue!
thank you.
from pycox.
Related Issues (20)
- Intuitions for padding model output columns?
- PyCOX data leaking HOT 1
- NLL PMF loss with partial PMF output
- How to use dropout in eval_ HOT 1
- is_monotonic should be update to is_monotonic_increasing HOT 1
- Issue in function cox_time.py HOT 1
- L1 and L2 penalty coxph HOT 1
- AssertionError: assert durations.shape[0] == surv.shape[1] == surv_idx.shape[0] == events.shape[0]
- METABRIC Covariates Subset HOT 1
- AttributeError: 'Series' object has no attribute 'is_monotonic' HOT 18
- about hazard value! HOT 2
- Reproduction of the results in JMLR19 paper HOT 1
- Calculating Estimated Population Survival Curve HOT 4
- Some question about the result of deephit_competing_risks HOT 2
- AttributeError: 'DeepHitSingle' object has no attribute 'state_dict' HOT 1
- ValueError: cannot convert float NaN to integer HOT 1
- Softmax layer and residual connections in DeepHitSingle model HOT 1
- _initialization of _internal failed
- TypeError: forward() missing 1 required positional argument: 'events'
- ValueError: cannot convert float NaN to integer 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 pycox.