colors/newsearch.py

import subprocess  # noqa: F401
import sys
from random import sample, seed

import numpy as np  # noqa: F401
from lightning_sdk import Machine, Studio  # noqa: F401

# consistency of randomly sampled experiments.
seed(19920921)

NUM_JOBS = 20

# Define the ranges or sets of values for each hyperparameter
# alpha_values = list(np.round(np.linspace(2, 4, 21), 4))
# learning_rate_values = list(np.round(np.logspace(-5, -3, 21), 5))
learning_rate_values = [1e-3]
# learning_rate_values = [5e-4]

# alpha_values = [0, .25, 0.5, 0.75, 1]  # alpha = 0 is unsupervised. alpha = 1 is supervised.
alpha_values = [0, 0.1]
widths = [2**k for k in range(4, 13)]
depths = [1, 2, 4, 8]
dropouts = [0, 0.5]
# widths, depths = [512], [4]

batch_size_values = [64, 256]
max_epochs_values = [720]  # at 12fps 720 frames = 60s
seeds = list(range(21, 1992))
optimizers = [
    # "Adagrad",
    "Adam",
    "SGD",
    # "AdamW",
    # "LBFGS",
    # "RAdam",
    # "RMSprop",
    # "Adadelta",
]

# Generate all possible combinations of hyperparameters
all_params = [
    (alpha, lr, bs, me, s, w, d, opt, dr)
    for alpha in alpha_values
    for lr in learning_rate_values
    for bs in batch_size_values
    for me in max_epochs_values
    for s in seeds
    for w in widths
    for d in depths
    for opt in optimizers
    for dr in dropouts
]


# perform random search with a limit
search_params = sample(all_params, min(NUM_JOBS, len(all_params)))

# --trainer.callbacks+ lightning.pytorch.callbacks.EarlyStopping \
# --trainer.callbacks.init_args.monitor hp_metric \

for idx, params in enumerate(search_params):
    a, lr, bs, me, s, w, d, opt, dr = params
    # cmd = f"cd ~/colors && python main.py --alpha {a} --lr {lr} --bs {bs} --max_epochs {me} --seed {s} --width {w}"
    cmd = f"""
cd ~/colors && python newmain.py fit \
--seed_everything {s} \
--data.batch_size {bs} \
--data.train_size 0 \
--data.val_size 10000 \
--model.alpha {a} \
--model.width {w} \
--model.depth {d} \
--model.bias true \
--model.loop true \
--model.transform tanh \
--model.dropout {dr} \
--trainer.min_epochs 10 \
--trainer.max_epochs {me} \
--trainer.log_every_n_steps 3 \
--trainer.check_val_every_n_epoch 1 \
--trainer.limit_val_batches 50 \
--trainer.callbacks callbacks.SaveImageCallback \
--trainer.callbacks.init_args.final_dir out \
--trainer.callbacks.init_args.save_interval 1 \
--optimizer torch.optim.{opt} \
--optimizer.init_args.lr {lr} \
--trainer.callbacks+ lightning.pytorch.callbacks.LearningRateFinder
"""
    # --lr_scheduler lightning.pytorch.cli.ReduceLROnPlateau \
    # --lr_scheduler.init_args.monitor hp_metric \
    # --lr_scheduler.init_args.factor 0.05 \
    # --lr_scheduler.init_args.patience 5 \
    # --lr_scheduler.init_args.cooldown 10 \
    # --lr_scheduler.init_args.verbose true
    print(f"Running {params}: {cmd}")
    try:
        studio = Studio("colors-animate-jobs")
        studio.install_plugin("jobs")
        job_plugin = studio.installed_plugins["jobs"]
        job_name = f"colors-animate-20240303-{idx+1}"
        job_plugin.run(cmd, machine=Machine.T4, name=job_name)

        # Run the command and wait for it to complete
        # subprocess.run(cmd, shell=True, check=True)
    except KeyboardInterrupt:
        print("Interrupted by user")
        sys.exit(1)
    # except subprocess.CalledProcessError:
    #     pass