项目地址:https://github.com/microsoft/OmniParser
欢迎关注我的个人repo并点亮星星:
https://github.com/xinyuwei-david/david-share.git/Multimodal-Models/
OmniParser
Box Threshold 和 IOU Threshold 是用于控制目标检测模型(YOLO模型)输出的两个重要参数。它们的具体含义如下:
Box Threshold(框阈值):
这个参数用来设置检测到的边界框(bounding box)的置信度阈值。
边界框置信度是模型对检测到的目标的置信程度。置信度越高,模型越确定这个边界框内包含一个目标。
Box Threshold 的值介于0.01到1.0之间。当检测到的边界框置信度低于这个阈值时,这个边界框将被过滤掉,不会出现在最终的输出结果中。
例如,如果 Box Threshold 设置为0.05,那么置信度低于0.05的边界框将被忽略。
IOU Threshold(交并比阈值):
IOU(Intersection over Union)是用来衡量两个边界框之间重叠程度的指标。
IOU Threshold 用来设置在进行非极大值抑制(NMS, Non-Maximum Suppression)时的阈值。NMS 是一种后处理步骤,用于移除重叠的边界框,只保留最有可能的那个。
IOU Threshold 的值介于0.01到1.0之间。当两个边界框的IOU值大于这个阈值时,置信度较低的边界框将被移除。
例如,如果 IOU Threshold 设置为0.1,那么当两个边界框的IOU值大于0.1时,置信度较低的那个边界框将被移除。
总结
Box Threshold:用于过滤掉置信度低于该阈值的边界框。
IOU Threshold:用于在非极大值抑制过程中移除重叠度高于该阈值的边界框。
这两个参数的设置可以帮助你调整目标检测的精度和召回率,以便在不同的应用场景中获得最佳的检测效果。
Text Box ID 0: Menu
Text Box ID 1: OpenAI_s_o1_evaluatio_
Text Box ID 2: Create
Text Box ID 3: Sign
Text Box ID 4: @iib
Text Box ID 5: All tools
Text Box ID 6: Edit
Text Box ID 7: Convert
Text Box ID 8: Find text or tools
Text Box ID 9: Al Assistant
Text Box ID 10: WinSCP
Text Box ID 11: Prompt
Text Box ID 12: github-local
Text Box ID 13: Suppose
Text Box ID 14: mecica
Text Box ID 15: following multiple-choice
Text Box ID 16: quesions and
Text Box ID 17: anation?
Text Box ID 18: 2
Text Box ID 19: siued icevelaping ereasldairhe
Text Box ID 20: Dou9ht She Rris prescribed Ocps
Text Box ID 21: ereaotbackeyticcectorat
Text Box ID 22: eiect
Text Box ID 23: Bamination
Text Box ID 24: breast?
Text Box ID 25: devel
Text Box ID 26: stage
Text Box ID 27: and pubic hair
Text Box ID 28: minimal (Tanner
Text Box ID 29: 31ag8
Text Box ID 30: most
Text Box ID 31: probable diagnosis?"
Text Box ID 32: opa
Text Box ID 33: -"Prematne
Text Box ID 34: opb" :
Text Box ID 35: syndrome"
Text Box ID 36: Miillenan
Text Box ID 37: agenesis
Text Box ID 38: opd"
Text Box ID 39: Androgen insensiivty"
Text Box ID 40: oCam
Text Box ID 41: Q1-preview
Text Box ID 42: most
Text Box ID 43: probable diagnosis for
Text Box ID 44: 6-year-old
Text Box ID 45: Androgen Insensitivity Syndrome
Text Box ID 46: (Option
Text Box ID 47: lanation:
Text Box ID 48: most probable diagnosis
Text Box ID 49: et'3 analyze
Text Box ID 50: key
Text Box ID 51: features presented:
Text Box ID 52: Amenorrhea:
Text Box ID 53: has
Text Box ID 54: started menstmuating by the
Text Box ID 55: Development:
Text Box ID 56: Staned
Text Box ID 57: loping breasts
Text Box ID 58: and -
Text Box ID 59: examination;
Text Box ID 60: breasts are
Text Box ID 61: developed (Tanner
Text Box ID 62: 4KSz#Ih
Text Box ID 63: Minimal Pubic Hair: She
Text Box ID 64: pubic hair (Tanner Stage
Text Box ID 65: and Athleticism:
Text Box ID 66: has
Text Box ID 67: normal heightand
Text Box ID 68: football player; indicating
Text Box ID 69: norma
Text Box ID 70: growth and development:
Text Box ID 71: Ineffectiveness
Text Box ID 72: Contraceptive
Text Box ID 73: wa; prescnbed
Text Box ID 74: years 2g0
Text Box ID 75: suggesting tat homonal therapy did not >
Text Box ID 76: menstuation:
Text Box ID 77: Interpreting the Clinical
Text Box ID 78: Development
Text Box ID 79: This combination
Text Box ID 80: that estrogen efect
Text Box ID 81: present (breast development), but androgen effect
Text Box ID 82: (lack
Text Box ID 83: pubic hair).
Text Box ID 84: 8fa978fe7_
Text Box ID 85: Amenorrhea
Text Box ID 86: Normal
Text Box ID 87: External Femal
Text Box ID 88: Genitalia and
Text Box ID 89: Uterus:
Text Box ID 90: conditions,
Text Box ID 91: may
Text Box ID 92: aosent Or
Text Box ID 93: underdeveloped
Text Box ID 94: eading
Text Box ID 95: primary amenorrhea despite
Text Box ID 96: secondary sexual characenstics_
Text Box ID 97: Differential Diagnoses:
Text Box ID 98: evaluate each option based
Text Box ID 99: te clinical features:
Text Box ID 100: Premature Ovarian
Text Box ID 101: Expected Findings:
Text Box ID 102: Cessation
Text Box ID 103: ovarian function
Text Box ID 104: #hz# YAY
Text Box ID 105: Decreased estrogen
Text Box ID 106: t4txt
Text Box ID 107: Lack
Text Box ID 108: breast de_
Text Box ID 109: opment
Text Box ID 110: regression_
Text Box ID 111: 249
Text Box ID 112: Presence
Text Box ID 113: pubic and
Text Box ID 114: hair
Text Box ID 115: adrenal androgens
Text Box ID 116: unaffected)-
Text Box ID 117: Conclusion: Unlikely; because
Text Box ID 118: paient has well-developed breasts and
Text Box ID 119: pubic
Text Box ID 120: 280
Text Box ID 121: Syndrome (45,XOJ:
Text Box ID 122: PDF
Text Box ID 123: OpenAI
Text Box ID 124: TIEIP
Text Box ID 125: 2024102_
Text Box ID 126: 249
Text Box ID 127: TE1B]
Text Box ID 128: 2024102_
Text Box ID 129: E-Sign
Text Box ID 130: Stage '
Icon Box ID 131: Character Highlighting Color
Icon Box ID 132: Up arrow
Icon Box ID 133: sending a message or email.
Icon Box ID 134: Home
Icon Box ID 135: Add comment
Icon Box ID 136: Link
Icon Box ID 137: Save
Icon Box ID 138: App launcher
Icon Box ID 139: Print
Icon Box ID 140: Redo
Icon Box ID 141: Email
Icon Box ID 142: Calendar
Icon Box ID 143: Notifications
Icon Box ID 144: Help (Alt+H)
Icon Box ID 145: a brick wall.
Icon Box ID 146: minimizing a window.
Icon Box ID 147: M0,0L9,0 4.5,5z
Icon Box ID 148: Close
Icon Box ID 149: minimizing a window.
Icon Box ID 150: Comment
Icon Box ID 151: Copy
本地目录结构:
(omni) root@a100vm:~/OmniParser/weights# ls -al ./*
-rw-r--r-- 1 root root 319 Oct 28 11:20 ./convert_safetensor_to_pt.py
./icon_caption_blip2:
total 14628564
drwxr-xr-x 2 root root 4096 Oct 28 13:40 .
drwxr-xr-x 5 root root 4096 Oct 28 11:47 ..
-rw-r--r-- 1 root root 1140 Oct 28 11:57 LICENSE
-rw-r--r-- 1 root root 985 Oct 28 11:57 config.json
-rw-r--r-- 1 root root 136 Oct 28 11:57 generation_config.json
-rw-r--r-- 1 root root 4998300711 Oct 9 22:58 pytorch_model-00001-of-00002.bin
-rw-r--r-- 1 root root 4998064248 Oct 24 14:31 pytorch_model-00001-of-00002.safetensors
-rw-r--r-- 1 root root 2491516218 Oct 9 22:58 pytorch_model-00002-of-00002.bin
-rw-r--r-- 1 root root 2491456448 Oct 24 14:31 pytorch_model-00002-of-00002.safetensors
-rw-r--r-- 1 root root 121726 Oct 28 12:01 pytorch_model.bin.index.json
./icon_caption_florence:
total 1058612
drwxr-xr-x 2 root root 4096 Oct 28 11:56 .
drwxr-xr-x 5 root root 4096 Oct 28 11:47 ..
-rw-r--r-- 1 root root 72204 Oct 28 11:40 LICENSE
-rw-r--r-- 1 root root 5663 Oct 28 11:54 config.json
-rw-r--r-- 1 root root 292 Oct 28 11:54 generation_config.json
-rw-r--r-- 1 root root 1083916964 Oct 25 23:19 model.safetensors
./icon_detect:
total 18276
drwxr-xr-x 2 root root 4096 Oct 28 11:52 .
drwxr-xr-x 5 root root 4096 Oct 28 11:47 ..
-rw-r--r-- 1 root root 400264 Oct 28 11:43 LICENSE
-rw-r--r-- 1 root root 12222450 Oct 28 13:45 best.pt
-rw-r--r-- 1 root root 6075790 Oct 24 23:11 model.safetensors
-rw-r--r-- 1 root root 1087 Oct 28 11:52 model.yaml
在A100上推理的的话,肯定是很快的:
通过笔记本的CPU也能运行,但比GPU的运行速度要慢很多。