robotics-diffusion-transformer
commited on
Upload openvla-7b+example_dataset+b16+lr-0.0005+lora-r32+dropout-0.0--image_aug+example_dataset+b16+lr-0.0005+lora-r32+dropout-0.0--image_aug/preprocessor_config.json
Browse files
openvla-7b+example_dataset+b16+lr-0.0005+lora-r32+dropout-0.0--image_aug+example_dataset+b16+lr-0.0005+lora-r32+dropout-0.0--image_aug/preprocessor_config.json
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoImageProcessor": "processing_prismatic.PrismaticImageProcessor",
|
4 |
+
"AutoProcessor": "processing_prismatic.PrismaticProcessor"
|
5 |
+
},
|
6 |
+
"image_processor_type": "PrismaticImageProcessor",
|
7 |
+
"image_resize_strategy": "resize-naive",
|
8 |
+
"input_sizes": [
|
9 |
+
[
|
10 |
+
3,
|
11 |
+
224,
|
12 |
+
224
|
13 |
+
],
|
14 |
+
[
|
15 |
+
3,
|
16 |
+
224,
|
17 |
+
224
|
18 |
+
]
|
19 |
+
],
|
20 |
+
"interpolations": [
|
21 |
+
"bicubic",
|
22 |
+
"bicubic"
|
23 |
+
],
|
24 |
+
"means": [
|
25 |
+
[
|
26 |
+
0.485,
|
27 |
+
0.456,
|
28 |
+
0.406
|
29 |
+
],
|
30 |
+
[
|
31 |
+
0.5,
|
32 |
+
0.5,
|
33 |
+
0.5
|
34 |
+
]
|
35 |
+
],
|
36 |
+
"processor_class": "PrismaticProcessor",
|
37 |
+
"stds": [
|
38 |
+
[
|
39 |
+
0.229,
|
40 |
+
0.224,
|
41 |
+
0.225
|
42 |
+
],
|
43 |
+
[
|
44 |
+
0.5,
|
45 |
+
0.5,
|
46 |
+
0.5
|
47 |
+
]
|
48 |
+
],
|
49 |
+
"tvf_crop_params": [
|
50 |
+
{
|
51 |
+
"output_size": [
|
52 |
+
224,
|
53 |
+
224
|
54 |
+
]
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"output_size": [
|
58 |
+
224,
|
59 |
+
224
|
60 |
+
]
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"tvf_do_letterbox": false,
|
64 |
+
"tvf_letterbox_fill": null,
|
65 |
+
"tvf_normalize_params": [
|
66 |
+
{
|
67 |
+
"inplace": false,
|
68 |
+
"mean": [
|
69 |
+
0.484375,
|
70 |
+
0.455078125,
|
71 |
+
0.40625
|
72 |
+
],
|
73 |
+
"std": [
|
74 |
+
0.228515625,
|
75 |
+
0.2236328125,
|
76 |
+
0.224609375
|
77 |
+
]
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"inplace": false,
|
81 |
+
"mean": [
|
82 |
+
0.5,
|
83 |
+
0.5,
|
84 |
+
0.5
|
85 |
+
],
|
86 |
+
"std": [
|
87 |
+
0.5,
|
88 |
+
0.5,
|
89 |
+
0.5
|
90 |
+
]
|
91 |
+
}
|
92 |
+
],
|
93 |
+
"tvf_resize_params": [
|
94 |
+
{
|
95 |
+
"antialias": true,
|
96 |
+
"interpolation": 3,
|
97 |
+
"max_size": null,
|
98 |
+
"size": [
|
99 |
+
224,
|
100 |
+
224
|
101 |
+
]
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"antialias": true,
|
105 |
+
"interpolation": 3,
|
106 |
+
"max_size": null,
|
107 |
+
"size": [
|
108 |
+
224,
|
109 |
+
224
|
110 |
+
]
|
111 |
+
}
|
112 |
+
],
|
113 |
+
"use_fused_vision_backbone": true
|
114 |
+
}
|