projects
/
culture.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Update.
[culture.git]
/
main.py
diff --git
a/main.py
b/main.py
index
704dff5
..
d961301
100755
(executable)
--- a/
main.py
+++ b/
main.py
@@
-33,7
+33,7
@@
parser.add_argument(
"--task",
type=str,
default="twotargets",
"--task",
type=str,
default="twotargets",
- help="byheart, learnop, guessop, twotargets, addition, picoclvr, mnist, maze, snake, stack, expr, rpl, grid",
+ help="byheart, learnop, guessop, twotargets, addition, picoclvr, mnist, maze, snake, stack, expr, rpl, grid
, qmlp
",
)
parser.add_argument("--log_filename", type=str, default="train.log", help=" ")
)
parser.add_argument("--log_filename", type=str, default="train.log", help=" ")
@@
-46,7
+46,7
@@
parser.add_argument("--max_percents_of_test_in_train", type=int, default=1)
########################################
########################################
-parser.add_argument("--nb_epochs", type=int, default=
None
)
+parser.add_argument("--nb_epochs", type=int, default=
25
)
parser.add_argument("--batch_size", type=int, default=None)
parser.add_argument("--batch_size", type=int, default=None)
@@
-159,11
+159,6
@@
parser.add_argument("--expr_result_max", type=int, default=99)
parser.add_argument("--expr_input_file", type=str, default=None)
parser.add_argument("--expr_input_file", type=str, default=None)
-##############################
-# World options
-
-parser.add_argument("--world_vqae_nb_epochs", type=int, default=25)
-
######################################################################
args = parser.parse_args()
######################################################################
args = parser.parse_args()
@@
-176,102
+171,88
@@
if args.result_dir is None:
######################################################################
default_task_args = {
######################################################################
default_task_args = {
+ "addition": {
+ "model": "352M",
+ "batch_size": 25,
+ "nb_train_samples": 250000,
+ "nb_test_samples": 10000,
+ },
"byheart": {
"model": "37M",
"byheart": {
"model": "37M",
- "nb_epochs": 2,
"batch_size": 25,
"nb_train_samples": 50000,
"nb_test_samples": 10000,
},
"batch_size": 25,
"nb_train_samples": 50000,
"nb_test_samples": 10000,
},
- "learnop": {
+ "expr": {
+ "model": "352M",
+ "batch_size": 25,
+ "nb_train_samples": 2500000,
+ "nb_test_samples": 10000,
+ },
+ "grid": {
"model": "37M",
"model": "37M",
- "nb_epochs": 15,
"batch_size": 25,
"batch_size": 25,
- "nb_train_samples": 50000,
+ "nb_train_samples":
2
50000,
"nb_test_samples": 10000,
},
"nb_test_samples": 10000,
},
+ "qmlp": {
+ "model": "37M",
+ "batch_size": 10,
+ "nb_train_samples": 100000,
+ "nb_test_samples": 1000,
+ },
"guessop": {
"model": "352M",
"guessop": {
"model": "352M",
- "nb_epochs": 5,
"batch_size": 25,
"nb_train_samples": 1000000,
"nb_test_samples": 10000,
},
"batch_size": 25,
"nb_train_samples": 1000000,
"nb_test_samples": 10000,
},
- "
twotargets
": {
+ "
learnop
": {
"model": "37M",
"model": "37M",
- "nb_epochs": 10,
"batch_size": 25,
"nb_train_samples": 50000,
"nb_test_samples": 10000,
},
"batch_size": 25,
"nb_train_samples": 50000,
"nb_test_samples": 10000,
},
- "addition": {
- "model": "352M",
- "nb_epochs": 50,
- "batch_size": 25,
- "nb_train_samples": 250000,
+ "maze": {
+ "model": "37M",
+ "batch_size": 5,
+ "nb_train_samples": 100000,
"nb_test_samples": 10000,
},
"picoclvr": {
"model": "37M",
"nb_test_samples": 10000,
},
"picoclvr": {
"model": "37M",
- "nb_epochs": 25,
"batch_size": 25,
"nb_train_samples": 250000,
"nb_test_samples": 10000,
},
"batch_size": 25,
"nb_train_samples": 250000,
"nb_test_samples": 10000,
},
- "mnist": {
- "model": "37M",
- "nb_epochs": 25,
- "batch_size": 10,
- "nb_train_samples": 60000,
- "nb_test_samples": 10000,
- },
- "maze": {
- "model": "37M",
- "nb_epochs": 25,
+ "rpl": {
+ "model": "352M",
"batch_size": 5,
"batch_size": 5,
- "nb_train_samples":
1
00000,
+ "nb_train_samples":
25
00000,
"nb_test_samples": 10000,
},
"snake": {
"model": "37M",
"nb_test_samples": 10000,
},
"snake": {
"model": "37M",
- "nb_epochs": 5,
"batch_size": 25,
"nb_train_samples": 250000,
"nb_test_samples": 10000,
},
"stack": {
"model": "37M",
"batch_size": 25,
"nb_train_samples": 250000,
"nb_test_samples": 10000,
},
"stack": {
"model": "37M",
- "nb_epochs": 15,
"batch_size": 25,
"nb_train_samples": 100000,
"nb_test_samples": 1000,
},
"batch_size": 25,
"nb_train_samples": 100000,
"nb_test_samples": 1000,
},
- "expr": {
- "model": "352M",
- "nb_epochs": 25,
- "batch_size": 25,
- "nb_train_samples": 2500000,
- "nb_test_samples": 10000,
- },
- "rpl": {
- "model": "122M",
- "nb_epochs": 50,
- "batch_size": 5,
- "nb_train_samples": 1000000,
- "nb_test_samples": 10000,
- },
- "world": {
+ "twotargets": {
"model": "37M",
"model": "37M",
- "nb_epochs": 10,
"batch_size": 25,
"batch_size": 25,
- "nb_train_samples":
25
000,
- "nb_test_samples": 1000,
+ "nb_train_samples":
50
000,
+ "nb_test_samples": 1000
0
,
},
},
- "
grid
": {
+ "
mnist
": {
"model": "37M",
"model": "37M",
- "nb_epochs": 25,
- "batch_size": 25,
- "nb_train_samples": 250000,
+ "batch_size": 10,
+ "nb_train_samples": 60000,
"nb_test_samples": 10000,
},
}
"nb_test_samples": 10000,
},
}
@@
-527,12
+508,12
@@
elif args.task == "grid":
device=device,
)
device=device,
)
-elif args.task == "
world
":
- task = tasks.
World
(
+elif args.task == "
qmlp
":
+ task = tasks.
QMLP
(
nb_train_samples=args.nb_train_samples,
nb_test_samples=args.nb_test_samples,
batch_size=args.batch_size,
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
,
+
result_dir=args.result_dir
,
logger=log_string,
device=device,
)
logger=log_string,
device=device,
)