/progressive_distillation_tsp_solver

Primary LanguageJupyter Notebook

PDAM: A neural network based instant TSP solver.

Progressive Distillation Attention Model (PDAM) is a neural network based instant TSP solver, which is able to solve a TSP instance within several millon seconds.

Dependencies

Quick start

For training TSP instances with 20 nodes and using rollout as REINFORCE baseline:

python run.py --graph_size 20 --baseline rollout --run_name 'tsp20_rollout'

Usage

Generating data

Training data is generated on the fly. To generate validation and test data (same as used in the paper) for all problems:

python generate_data.py --problem all --name validation --seed 4321
python generate_data.py --problem all --name test --seed 1234

Training

For training TSP instances with 20 nodes and using rollout as REINFORCE baseline and using the generated validation set:

python run.py --graph_size 20 --baseline rollout --run_name 'tsp20_rollout' --val_dataset data/tsp/tsp20_validation_seed4321.pkl

Multiple GPUs

By default, training will happen on all available GPUs. To disable CUDA at all, add the flag --no_cuda. Set the environment variable CUDA_VISIBLE_DEVICES to only use specific GPUs:

CUDA_VISIBLE_DEVICES=2,3 python run.py

Note that using multiple GPUs has limited efficiency for small problem sizes (up to 50 nodes).

Warm start

You can initialize a run using a pretrained model by using the --load_path option:

python run.py --graph_size 100 --load_path pretrained/tsp_100/epoch-99.pt

The --load_path option can also be used to load an earlier run, in which case also the optimizer state will be loaded:

python run.py --graph_size 20 --load_path 'outputs/tsp_20/tsp20_rollout_{datetime}/epoch-0.pt'

The --resume option can be used instead of the --load_path option, which will try to resume the run, e.g. load additionally the baseline state, set the current epoch/step counter and set the random number generator state.

Progressive Distillation

You can set --progressive_distillation parameter to enable progressive distillation. --beta is the weight of progressive distillation. --local_size is local window size ratio, and --beta_decay is every epoch beta will decay.

python run.py --graph_size 20 --progressive_distillation  --local_size 0.4 --beta_decay 0.95 --load_path 'outputs/tsp_20/tsp20_rollout_{datetime}/epoch-0.pt'

Evaluation

To evaluate a model, you can add the --eval-only flag to run.py, or use eval.py, which will additionally measure timing and save the results:

python eval.py data/tsp/tsp20_test_seed1234.pkl --model pretrained/tsp_20 --decode_strategy greedy

If the epoch is not specified, by default the last one in the folder will be used.

Sampling

To report the best of 1280 sampled solutions, use

python eval.py data/tsp/tsp20_test_seed1234.pkl --model pretrained/tsp_20 --decode_strategy sample --width 1280 --eval_batch_size 1

Beam Search (not in the paper) is also recently added and can be used using --decode_strategy bs --width {beam_size}.

Other options and help

python run.py -h
python eval.py -h