Datasets:

antofuller
/

mini-VTAB

image imagewidth (px) 224 224	img_idx int64 0 999	label int64 0 101
	0	76
	100	101
	101	40
	102	45
	103	27
	104	0
	105	13
	106	57
	107	4
	108	69
	109	7
	10	30
	110	90
	111	63
	112	55
	113	28
	114	7
	115	100
	116	60
	117	42
	118	89
	119	98
	11	94
	120	67
	121	96
	122	32
	123	11
	124	91
	125	28
	126	62
	127	63
	128	78
	129	62
	12	11
	130	39
	131	40
	132	17
	133	39
	134	47
	135	56
	136	61
	137	73
	138	91
	139	48
	13	38
	140	54
	141	76
	142	13
	143	0
	144	98
	145	52
	146	97
	147	90
	148	100
	149	85
	14	57
	150	92
	151	69
	152	44
	153	46
	154	29
	155	71
	156	78
	157	67
	158	74
	159	1
	15	42
	160	79
	161	21
	162	42
	163	88
	164	82
	165	51
	166	12
	167	5
	168	82
	169	26
	16	30
	170	25
	171	90
	172	60
	173	99
	174	89
	175	83
	176	70
	177	17
	178	80
	179	57
	17	101
	180	63
	181	24
	182	12
	183	69
	184	75
	185	24
	186	47
	187	3
	188	8
	189	19
	18	68

End of preview. Expand in Data Studio

Mini-VTAB

A collection of VTAB (Visual Task Adaptation Benchmark) datasets. We sampled 1K training samples and 1K testing samples for each task.

Tasks

datasets = [
    "caltech101",
    "cifar10",
    "cifar100",
    "dtd",
    "flowers",
    "pets",
    "sun397",
    "svhn",

    "pcam",
    "eurosat",
    "resisc45",
    "diabetic_retinopathy",

    "clevr_count_all",
    "clevr_closest_object_distance",
    "dmlab",
    "dsprites_label_x_position",
    "dsprites_label_y_position",
    "dsprites_label_orientation",
    "kitti_distance",
    "smallnorb_label_azimuth",
    "smallnorb_label_elevation",
]

Usage

from datasets import load_dataset

# Load a specific task
ds = load_dataset("antofuller/mini-vtab", "cifar10")

# Access splits
train_ds = ds["train"]
test_ds = ds["test"]

# Or load a specific split directly
train_ds = load_dataset("antofuller/mini-VTAB", "cifar10", split="train")

Downloads last month: 53

Size of downloaded dataset files:

1.98 GB

Size of the auto-converted Parquet files:

1.98 GB

Number of rows:

41,711

image imagewidth (px) 224 224	img_idx int64 0 999	label int64 0 101
	0	76
	100	101
	101	40
	102	45
	103	27
	104	0
	105	13
	106	57
	107	4
	108	69
	109	7
	10	30
	110	90
	111	63
	112	55
	113	28
	114	7
	115	100
	116	60
	117	42
	118	89
	119	98
	11	94
	120	67
	121	96
	122	32
	123	11
	124	91
	125	28
	126	62
	127	63
	128	78
	129	62
	12	11
	130	39
	131	40
	132	17
	133	39
	134	47
	135	56
	136	61
	137	73
	138	91
	139	48
	13	38
	140	54
	141	76
	142	13
	143	0
	144	98
	145	52
	146	97
	147	90
	148	100
	149	85
	14	57
	150	92
	151	69
	152	44
	153	46
	154	29
	155	71
	156	78
	157	67
	158	74
	159	1
	15	42
	160	79
	161	21
	162	42
	163	88
	164	82
	165	51
	166	12
	167	5
	168	82
	169	26
	16	30
	170	25
	171	90
	172	60
	173	99
	174	89
	175	83
	176	70
	177	17
	178	80
	179	57
	17	101
	180	63
	181	24
	182	12
	183	69
	184	75
	185	24
	186	47
	187	3
	188	8
	189	19
	18	68

image imagewidth (px) 224 224	img_idx int64 0 999	label int64 0 101
	0	76
	100	101
	101	40
	102	45
	103	27
	104	0
	105	13
	106	57
	107	4
	108	69
	109	7
	10	30
	110	90
	111	63
	112	55
	113	28
	114	7
	115	100
	116	60
	117	42
	118	89
	119	98
	11	94
	120	67
	121	96
	122	32
	123	11
	124	91
	125	28
	126	62
	127	63
	128	78
	129	62
	12	11
	130	39
	131	40
	132	17
	133	39
	134	47
	135	56
	136	61
	137	73
	138	91
	139	48
	13	38
	140	54
	141	76
	142	13
	143	0
	144	98
	145	52
	146	97
	147	90
	148	100
	149	85
	14	57
	150	92
	151	69
	152	44
	153	46
	154	29
	155	71
	156	78
	157	67
	158	74
	159	1
	15	42
	160	79
	161	21
	162	42
	163	88
	164	82
	165	51
	166	12
	167	5
	168	82
	169	26
	16	30
	170	25
	171	90
	172	60
	173	99
	174	89
	175	83
	176	70
	177	17
	178	80
	179	57
	17	101
	180	63
	181	24
	182	12
	183	69
	184	75
	185	24
	186	47
	187	3
	188	8
	189	19
	18	68

image imagewidth (px) 224 224	img_idx int64 0 999	label int64 0 101
	0	76
	100	101
	101	40
	102	45
	103	27
	104	0
	105	13
	106	57
	107	4
	108	69
	109	7
	10	30
	110	90
	111	63
	112	55
	113	28
	114	7
	115	100
	116	60
	117	42
	118	89
	119	98
	11	94
	120	67
	121	96
	122	32
	123	11
	124	91
	125	28
	126	62
	127	63
	128	78
	129	62
	12	11
	130	39
	131	40
	132	17
	133	39
	134	47
	135	56
	136	61
	137	73
	138	91
	139	48
	13	38
	140	54
	141	76
	142	13
	143	0
	144	98
	145	52
	146	97
	147	90
	148	100
	149	85
	14	57
	150	92
	151	69
	152	44
	153	46
	154	29
	155	71
	156	78
	157	67
	158	74
	159	1
	15	42
	160	79
	161	21
	162	42
	163	88
	164	82
	165	51
	166	12
	167	5
	168	82
	169	26
	16	30
	170	25
	171	90
	172	60
	173	99
	174	89
	175	83
	176	70
	177	17
	178	80
	179	57
	17	101
	180	63
	181	24
	182	12
	183	69
	184	75
	185	24
	186	47
	187	3
	188	8
	189	19
	18	68