Update.

[picoclvr.git] / main.py

diff --git a/main.py b/main.py
index 69731ff..e855b06 100755 (executable)
--- a/main.py
+++ b/main.py
@@ -33,7 +33,7 @@ parser.add_argument(
     "--task",
     type=str,
     default="twotargets",
-    help="byheart, learnop, guessop, mixing, memory, twotargets, addition, picoclvr, mnist, maze, snake, stack, expr, rpl, grid, qmlp",
+    help="file, byheart, learnop, guessop, mixing, memory, twotargets, addition, picoclvr, mnist, maze, snake, stack, expr, rpl, grid, qmlp, escape",
 )
 
 parser.add_argument("--log_filename", type=str, default="train.log", help=" ")
@@ -86,6 +86,13 @@ parser.add_argument("--overwrite_results", action="store_true", default=False)
 
 parser.add_argument("--checkpoint_name", type=str, default="checkpoint.pth")
 
+##############################
+# filetask
+
+parser.add_argument("--filetask_train_file", type=str, default=None)
+
+parser.add_argument("--filetask_test_file", type=str, default=None)
+
 ##############################
 # rpl options
 
@@ -104,6 +111,8 @@ parser.add_argument("--rpl_no_prog", action="store_true", default=False)
 
 parser.add_argument("--grid_size", type=int, default=6)
 
+parser.add_argument("--grid_fraction_play", type=float, default=0)
+
 ##############################
 # picoclvr options
 
@@ -166,6 +175,17 @@ parser.add_argument("--mixing_hard", action="store_true", default=False)
 
 parser.add_argument("--mixing_deterministic_start", action="store_true", default=False)
 
+##############################
+# escape options
+
+parser.add_argument("--escape_height", type=int, default=5)
+
+parser.add_argument("--escape_width", type=int, default=7)
+
+parser.add_argument("--escape_T", type=int, default=25)
+
+parser.add_argument("--escape_nb_walls", type=int, default=5)
+
 ######################################################################
 
 args = parser.parse_args()
@@ -178,6 +198,12 @@ if args.result_dir is None:
 ######################################################################
 
 default_task_args = {
+    "file": {
+        "model": "37M",
+        "batch_size": 25,
+        "nb_train_samples": 250000,
+        "nb_test_samples": 10000,
+    },
     "addition": {
         "model": "352M",
         "batch_size": 25,
@@ -274,6 +300,12 @@ default_task_args = {
         "nb_train_samples": 60000,
         "nb_test_samples": 10000,
     },
+    "escape": {
+        "model": "37M",
+        "batch_size": 25,
+        "nb_train_samples": 25000,
+        "nb_test_samples": 10000,
+    },
 }
 
 if args.task in default_task_args:
@@ -388,7 +420,22 @@ picoclvr_pruner_eval = (
 
 ######################################################################
 
-if args.task == "byheart":
+if args.task == "file":
+    assert (
+        args.filetask_train_file is not None and args.filetask_test_file is not None
+    ), "You have to specify the task train and test files"
+    task = tasks.TaskFromFile(
+        args.filetask_train_file,
+        args.filetask_test_file,
+        nb_train_samples=args.nb_train_samples,
+        nb_test_samples=args.nb_test_samples,
+        batch_size=args.batch_size,
+        shuffle=True,
+        device=device,
+    )
+    args.max_percents_of_test_in_train = 0
+
+elif args.task == "byheart":
     task = tasks.SandBox(
         problem=problems.ProblemByHeart(),
         nb_train_samples=args.nb_train_samples,
@@ -554,6 +601,7 @@ elif args.task == "grid":
         nb_test_samples=args.nb_test_samples,
         batch_size=args.batch_size,
         size=args.grid_size,
+        fraction_play=args.grid_fraction_play,
         logger=log_string,
         device=device,
     )
@@ -568,6 +616,19 @@ elif args.task == "qmlp":
         device=device,
     )
 
+elif args.task == "escape":
+    task = tasks.Escape(
+        nb_train_samples=args.nb_train_samples,
+        nb_test_samples=args.nb_test_samples,
+        batch_size=args.batch_size,
+        height=args.escape_height,
+        width=args.escape_width,
+        T=args.escape_T,
+        nb_walls=args.escape_nb_walls,
+        logger=log_string,
+        device=device,
+    )
+
 else:
     raise ValueError(f"Unknown task {args.task}")