add RAM usage with CachDataset
Browse files- README.md +11 -1
- configs/metadata.json +2 -1
- docs/README.md +11 -1
README.md
CHANGED
@@ -79,7 +79,7 @@ Example dataset.json
|
|
79 |
}
|
80 |
```
|
81 |
|
82 |
-
## Training
|
83 |
The training was performed with the following:
|
84 |
|
85 |
- GPU: at least 12GB of GPU memory
|
@@ -89,6 +89,16 @@ The training was performed with the following:
|
|
89 |
- Learning Rate: 1e-4
|
90 |
- Loss: DiceLoss
|
91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
|
93 |
## Input
|
94 |
5 channels
|
|
|
79 |
}
|
80 |
```
|
81 |
|
82 |
+
## Training Configuration
|
83 |
The training was performed with the following:
|
84 |
|
85 |
- GPU: at least 12GB of GPU memory
|
|
|
89 |
- Learning Rate: 1e-4
|
90 |
- Loss: DiceLoss
|
91 |
|
92 |
+
### Memory Consumption
|
93 |
+
|
94 |
+
- Dataset Manager: CacheDataset
|
95 |
+
- Data Size: 13,136 PNG images
|
96 |
+
- Cache Rate: 1.0
|
97 |
+
- Single GPU - System RAM Usage: 4.7G
|
98 |
+
|
99 |
+
### Memory Consumption Warning
|
100 |
+
|
101 |
+
If you face memory issues with CacheDataset, you can either switch to a regular Dataset class or lower the caching rate `cache_rate` in the configurations within range $(0, 1)$ to minimize the System RAM requirements.
|
102 |
|
103 |
## Input
|
104 |
5 channels
|
configs/metadata.json
CHANGED
@@ -1,7 +1,8 @@
|
|
1 |
{
|
2 |
"schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
|
3 |
-
"version": "0.1.
|
4 |
"changelog": {
|
|
|
5 |
"0.1.1": "deterministic retrain benchmark and add link",
|
6 |
"0.1.0": "fix mgpu finalize issue",
|
7 |
"0.0.9": "Update README Formatting",
|
|
|
1 |
{
|
2 |
"schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
|
3 |
+
"version": "0.1.2",
|
4 |
"changelog": {
|
5 |
+
"0.1.2": "add RAM usage with CachDataset",
|
6 |
"0.1.1": "deterministic retrain benchmark and add link",
|
7 |
"0.1.0": "fix mgpu finalize issue",
|
8 |
"0.0.9": "Update README Formatting",
|
docs/README.md
CHANGED
@@ -72,7 +72,7 @@ Example dataset.json
|
|
72 |
}
|
73 |
```
|
74 |
|
75 |
-
## Training
|
76 |
The training was performed with the following:
|
77 |
|
78 |
- GPU: at least 12GB of GPU memory
|
@@ -82,6 +82,16 @@ The training was performed with the following:
|
|
82 |
- Learning Rate: 1e-4
|
83 |
- Loss: DiceLoss
|
84 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
|
86 |
## Input
|
87 |
5 channels
|
|
|
72 |
}
|
73 |
```
|
74 |
|
75 |
+
## Training Configuration
|
76 |
The training was performed with the following:
|
77 |
|
78 |
- GPU: at least 12GB of GPU memory
|
|
|
82 |
- Learning Rate: 1e-4
|
83 |
- Loss: DiceLoss
|
84 |
|
85 |
+
### Memory Consumption
|
86 |
+
|
87 |
+
- Dataset Manager: CacheDataset
|
88 |
+
- Data Size: 13,136 PNG images
|
89 |
+
- Cache Rate: 1.0
|
90 |
+
- Single GPU - System RAM Usage: 4.7G
|
91 |
+
|
92 |
+
### Memory Consumption Warning
|
93 |
+
|
94 |
+
If you face memory issues with CacheDataset, you can either switch to a regular Dataset class or lower the caching rate `cache_rate` in the configurations within range $(0, 1)$ to minimize the System RAM requirements.
|
95 |
|
96 |
## Input
|
97 |
5 channels
|