Hugging Face's logo

Hsueh1001
/
yolo

Object Detection
Transformers
PyTorch
yolos
Inference Endpoints
Model card Files Community
yolo / config.json
Hsueh1001's picture
Hsueh1001
Upload YolosForObjectDetection
68c3ea2
raw
history blame
13 kB
{
"_name_or_path": "C:\\Users\\eatin\\Desktop\\ML\\yolov7",
"anchors": [
[
12,
16,
19,
36,
40,
28
],
[
36,
75,
76,
55,
72,
146
],
[
142,
110,
192,
243,
459,
401
]
],
"architectures": [
"YolosForObjectDetection"
],
"attention_probs_dropout_prob": 0.0,
"auxiliary_loss": false,
"backbone": [
[
-1,
1,
"Conv",
[
32,
3,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
2
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
2
]
],
[
-1,
1,
"Conv",
[
64,
1,
1
]
],
[
-2,
1,
"Conv",
[
64,
1,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
[
-1,
-3,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"MP",
[]
],
[
-1,
1,
"Conv",
[
128,
1,
1
]
],
[
-3,
1,
"Conv",
[
128,
1,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
2
]
],
[
[
-1,
-3
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
128,
1,
1
]
],
[
-2,
1,
"Conv",
[
128,
1,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
[
-1,
-3,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
512,
1,
1
]
],
[
-1,
1,
"MP",
[]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-3,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
2
]
],
[
[
-1,
-3
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-2,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
[
-1,
-3,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
1024,
1,
1
]
],
[
-1,
1,
"MP",
[]
],
[
-1,
1,
"Conv",
[
512,
1,
1
]
],
[
-3,
1,
"Conv",
[
512,
1,
1
]
],
[
-1,
1,
"Conv",
[
512,
3,
2
]
],
[
[
-1,
-3
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-2,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
[
-1,
-3,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
1024,
1,
1
]
]
],
"bbox_cost": 5,
"bbox_loss_coefficient": 5,
"class_cost": 1,
"conf_threshold": 0.1,
"depth_multiple": 1.0,
"eos_coefficient": 0.1,
"giou_cost": 2,
"giou_loss_coefficient": 2,
"head": [
[
-1,
1,
"SPPCSPC",
[
512
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"nn.Upsample",
[
"None",
2,
"nearest"
]
],
[
37,
1,
"Conv",
[
256,
1,
1
]
],
[
[
-1,
-2
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-2,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
[
-1,
-2,
-3,
-4,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"Conv",
[
128,
1,
1
]
],
[
-1,
1,
"nn.Upsample",
[
"None",
2,
"nearest"
]
],
[
24,
1,
"Conv",
[
128,
1,
1
]
],
[
[
-1,
-2
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
128,
1,
1
]
],
[
-2,
1,
"Conv",
[
128,
1,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
-1,
1,
"Conv",
[
64,
3,
1
]
],
[
[
-1,
-2,
-3,
-4,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
128,
1,
1
]
],
[
-1,
1,
"MP",
[]
],
[
-1,
1,
"Conv",
[
128,
1,
1
]
],
[
-3,
1,
"Conv",
[
128,
1,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
2
]
],
[
[
-1,
-3,
63
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-2,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
-1,
1,
"Conv",
[
128,
3,
1
]
],
[
[
-1,
-2,
-3,
-4,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"MP",
[]
],
[
-1,
1,
"Conv",
[
256,
1,
1
]
],
[
-3,
1,
"Conv",
[
256,
1,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
2
]
],
[
[
-1,
-3,
51
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
512,
1,
1
]
],
[
-2,
1,
"Conv",
[
512,
1,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
-1,
1,
"Conv",
[
256,
3,
1
]
],
[
[
-1,
-2,
-3,
-4,
-5,
-6
],
1,
"Concat",
[
1
]
],
[
-1,
1,
"Conv",
[
512,
1,
1
]
],
[
75,
1,
"RepConv",
[
256,
3,
1
]
],
[
88,
1,
"RepConv",
[
512,
3,
1
]
],
[
101,
1,
"RepConv",
[
1024,
3,
1
]
],
[
[
102,
103,
104
],
1,
"IDetect",
[
"nc",
"anchors"
]
]
],
"hidden_act": "gelu",
"hidden_dropout_prob": 0.0,
"hidden_size": 768,
"image_size": [
512,
864
],
"initializer_range": 0.02,
"input_size": [
640,
640
],
"intermediate_size": 3072,
"iou_threshold": 0.1,
"layer_norm_eps": 1e-12,
"model_type": "yolos",
"names": [
"person",
"bicycle",
"car",
"motorcycle",
"airplane",
"bus",
"train",
"truck",
"boat",
"traffic light",
"fire hydrant",
"stop sign",
"parking meter",
"bench",
"bird",
"cat",
"dog",
"horse",
"sheep",
"cow",
"elephant",
"bear",
"zebra",
"giraffe",
"backpack",
"umbrella",
"handbag",
"tie",
"suitcase",
"frisbee",
"skis",
"snowboard",
"sports ball",
"kite",
"baseball bat",
"baseball glove",
"skateboard",
"surfboard",
"tennis racket",
"bottle",
"wine glass",
"cup",
"fork",
"knife",
"spoon",
"bowl",
"banana",
"apple",
"sandwich",
"orange",
"broccoli",
"carrot",
"hot dog",
"pizza",
"donut",
"cake",
"chair",
"couch",
"potted plant",
"bed",
"dining table",
"toilet",
"tv",
"laptop",
"mouse",
"remote",
"keyboard",
"cell phone",
"microwave",
"oven",
"toaster",
"sink",
"refrigerator",
"book",
"clock",
"vase",
"scissors",
"teddy bear",
"hair drier",
"toothbrush"
],
"nc": 80,
"nms_threshold": 0.1,
"num_attention_heads": 12,
"num_channels": 3,
"num_detection_tokens": 100,
"num_hidden_layers": 12,
"patch_size": 16,
"qkv_bias": true,
"save_txt": true,
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"use_mid_position_embeddings": true,
"weights": "yolov7.pt",
"width_multiple": 1.0
}