Training: Step 2 about clevr-iep HOT 9 OPEN

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.