X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=main.py;h=e18887b1998adc31da6c914519b2ba7ff049aece;hb=0f580d4facb4b4b485d0a38d62d06c0639715b77;hp=003028a819ccc5e8882435dbb817ca59aa128ba0;hpb=5aee50805cfad1dd49bbf30b30fe65b05e03de78;p=picoclvr.git

diff --git a/main.py b/main.py
index 003028a..e18887b 100755
--- a/main.py
+++ b/main.py
@@ -14,6 +14,7 @@ import torch, torchvision
 from torch import nn
 from torch.nn import functional as F
 
+import ffutils
 import mygpt, tasks
 
 ######################################################################
@@ -34,8 +35,8 @@ parser = argparse.ArgumentParser(
 parser.add_argument(
     "--task",
     type=str,
-    default="picoclvr",
-    help="picoclvr, mnist, maze, snake, stack, expr",
+    default="sandbox",
+    help="sandbox, picoclvr, mnist, maze, snake, stack, expr, world",
 )
 
 parser.add_argument("--log_filename", type=str, default="train.log", help=" ")
@@ -110,7 +111,7 @@ parser.add_argument("--snake_nb_colors", type=int, default=5)
 parser.add_argument("--snake_length", type=int, default=200)
 
 ##############################
-# Snake options
+# Stack options
 
 parser.add_argument("--stack_nb_steps", type=int, default=100)
 
@@ -125,7 +126,18 @@ parser.add_argument("--stack_fraction_values_for_train", type=float, default=0.7
 
 parser.add_argument("--expr_nb_variables", type=int, default=5)
 
-parser.add_argument("--expr_sequence_length", type=int, default=30)
+parser.add_argument("--expr_sequence_length", type=int, default=40)
+
+parser.add_argument("--expr_operand_max", type=int, default=9)
+
+parser.add_argument("--expr_result_max", type=int, default=99)
+
+parser.add_argument("--expr_input_file", type=str, default=None)
+
+##############################
+# World options
+
+parser.add_argument("--world_vqae_nb_epochs", type=int, default=25)
 
 ######################################################################
 
@@ -139,6 +151,12 @@ if args.result_dir is None:
 ######################################################################
 
 default_args = {
+    "sandbox": {
+        "nb_epochs": 10,
+        "batch_size": 25,
+        "nb_train_samples": 25000,
+        "nb_test_samples": 10000,
+    },
     "picoclvr": {
         "nb_epochs": 25,
         "batch_size": 25,
@@ -170,11 +188,17 @@ default_args = {
         "nb_test_samples": 1000,
     },
     "expr": {
-        "nb_epochs": 50,
+        "nb_epochs": 40,
         "batch_size": 25,
-        "nb_train_samples": 250000,
+        "nb_train_samples": 1000000,
         "nb_test_samples": 10000,
     },
+    "world": {
+        "nb_epochs": 10,
+        "batch_size": 25,
+        "nb_train_samples": 25000,
+        "nb_test_samples": 1000,
+    },
 }
 
 if args.task in default_args:
@@ -240,7 +264,16 @@ picoclvr_pruner_eval = (
 
 ######################################################################
 
-if args.task == "picoclvr":
+if args.task == "sandbox":
+    task = tasks.SandBox(
+        nb_train_samples=args.nb_train_samples,
+        nb_test_samples=args.nb_test_samples,
+        batch_size=args.batch_size,
+        logger=log_string,
+        device=device,
+    )
+
+elif args.task == "picoclvr":
     task = tasks.PicoCLVR(
         nb_train_samples=args.nb_train_samples,
         nb_test_samples=args.nb_test_samples,
@@ -305,7 +338,19 @@ elif args.task == "expr":
         nb_test_samples=args.nb_test_samples,
         nb_variables=args.expr_nb_variables,
         sequence_length=args.expr_sequence_length,
+        operand_max=args.expr_operand_max,
+        result_max=args.expr_result_max,
+        batch_size=args.batch_size,
+        device=device,
+    )
+
+elif args.task == "world":
+    task = tasks.World(
+        nb_train_samples=args.nb_train_samples,
+        nb_test_samples=args.nb_test_samples,
         batch_size=args.batch_size,
+        vqae_nb_epochs=args.world_vqae_nb_epochs,
+        logger=log_string,
         device=device,
     )
 
@@ -366,6 +411,20 @@ else:
 
 ######################################################################
 
+if args.task == "expr" and args.expr_input_file is not None:
+    task.produce_results(
+        nb_epochs_finished,
+        model,
+        args.result_dir,
+        log_string,
+        args.deterministic_synthesis,
+        args.expr_input_file,
+    )
+
+    exit(0)
+
+######################################################################
+
 nb_epochs = args.nb_epochs if args.nb_epochs > 0 else nb_epochs_default
 
 # Compute the entropy of the training tokens