Comments (9)
Yes, it's the learning rate. It should be decreased to 1e-5, and then step 2 works. Note, that it will indeed use the groundtruth programs in Step 2.
from clevr-iep.
Same question here. According to TRAINING.md
, in Step 2 "we train the execution engine, using programs predicted from the program generator in the previous step". In train_model.py
line 238 says "train execution engine with ground-truth programs". Can you please explain this discrepancy?
In any case, when I train --model_type=EE
without Step 1 pretraining, the learning doesn't really progress (still at ~50% accuracy after 100000) iterations.
from clevr-iep.
Can you try training longer?
from clevr-iep.
have you solve the problem?
from clevr-iep.
But how about the val accuracy?
from clevr-iep.
I get smth like 95-96%, which is what is reported in the paper.
from clevr-iep.
@rizar can you please tell how did you get 95-96% accuracy by directly training the execution engine using the ground truth programs (as in step 2). My accuracy is oscillating around 0.47 even after 5000 iterations when using lr = 1e-5
from clevr-iep.
Can you try training longer?
Thanks to you, I trained the execution engine for 100000 iterations with lr=1e-5 and got around 89% accuracy. Actually, accuracy increased quite slowly initially, and then between 40k and 60k iterations, it increased steeply.
from clevr-iep.
minimum pc specs you all are using to train this model, can anyone suggest
from clevr-iep.
Related Issues (20)
- error while trying to save predictions in output_h5 HOT 1
- Loss calculation !!
- NoneType HOT 2
- a possible typo! HOT 9
- IndexError! HOT 1
- RuntimeError: inconsistent tensor size HOT 2
- RuntimeError: expand(torch.LongTensor{[1, 1]}, size=[1]): the number of sizes provided (1) must be greater or equal to the number of dimensions in the tensor (2) at seq2seq.py, line 183, in reinforce_sample y[:, t][not_done] = cur_output_data[not_done] HOT 2
- torch-0.1.11.post5-cp35-cp35m-linux_x86_64.whl is not a supported wheel on this platform. HOT 2
- File "clevr-iep/iep/models/seq2seq.py", line 57, in get_dims T_out = y.size(1) if y is not None else None HOT 1
- RuntimeError: CUDA error: out of memory for GTX 1080 Ti HOT 1
- ValueError: unrecognized program format HOT 3
- Unable to download CLEVR dataset HOT 5
- IndexError:too many indices for tensor of dimension 1 HOT 16
- line 81, in __getitem__\n fn_str = self.vocab[\'program_idx_to_token\'][fn_idx]\nKeyError: tensor(1)\n' HOT 2
- RuntimeError: CuDNN error: CUDNN_STATUS_SUCCESS HOT 1
- Question: A list of program modules HOT 1
- KeyError: 'function' not found HOT 1
- Training data is incomplete?
- Are there other ways to get results on test set?
- Undefined variable
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 clevr-iep.