diff --git a/main.py b/main.py index df1420e..84915d2 100644 --- a/main.py +++ b/main.py @@ -40,6 +40,9 @@ def parse_args(): default=3, help="Number of workers for data loading", ) + parser.add_argument( + "--width", type=int, default=128, help="Max width of network." + ) # Parse arguments args = parser.parse_args() @@ -87,6 +90,7 @@ if __name__ == "__main__": alpha=args.alpha, learning_rate=args.lr, batch_size=args.bs, + width=args.width, ) # Initialize model with parsed arguments diff --git a/model.py b/model.py index 68b9d7b..579931f 100644 --- a/model.py +++ b/model.py @@ -86,9 +86,9 @@ class ColorTransformerModel(pl.LightningModule): # Neural network layers self.network = nn.Sequential( - nn.Linear(3, 256), + nn.Linear(3, self.hparams.width), nn.ReLU(), - nn.Linear(256, 64), + nn.Linear(self.hparams.width, 64), nn.ReLU(), nn.Linear(64, 1), ) diff --git a/search.py b/search.py index 241fd43..3936683 100644 --- a/search.py +++ b/search.py @@ -21,6 +21,7 @@ job_plugin = studio.installed_plugins["jobs"] # alpha_values = list(np.round(np.linspace(2, 4, 21), 4)) learning_rate_values = list(np.round(np.logspace(-5, -3, 21), 5)) alpha_values = [0, 1, 2] +widths = [64, 128, 256, 512] # learning_rate_values = [5e-4] batch_size_values = [32, 64, 128] max_epochs_values = [500] @@ -28,12 +29,13 @@ seeds = list(range(21, 1992)) # Generate all possible combinations of hyperparameters all_params = [ - (alpha, lr, bs, me, s) + (alpha, lr, bs, me, s, w) 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 ] @@ -41,8 +43,8 @@ all_params = [ search_params = sample(all_params, min(NUM_JOBS, len(all_params))) for idx, params in enumerate(search_params): - a, lr, bs, me, s = params - cmd = f"cd ~/colors && python main.py --alpha {a} --lr {lr} --bs {bs} --max_epochs {me} --seed {s}" + a, lr, bs, me, s, w = params + cmd = f"cd ~/colors && python main.py --alpha {a} --lr {lr} --bs {bs} --max_epochs {me} --seed {s} --width {w}" # job_name = f"color2_{bs}_{a}_{lr:2.2e}" # job_plugin.run(cmd, machine=Machine.T4, name=job_name) print(f"Running {params}: {cmd}")