Specifications for Importing a Manifest File

Image Classification

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28

{
    "source":"s3://path/to/image1.jpg",
    "usage":"TRAIN",
    "hard":"true",
    "hard-coefficient":0.8,
    "id":"0162005993f8065ef47eefb59d1e4970",
    "annotation": [
        {
            "type": "modelarts/image_classification",
            "name": "cat",
            "property": {
                "color":"white",
                "kind":"Persian cat"            
            },
            "hard":"true",
            "hard-coefficient":0.8,
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"        
        },
        {
            "type": "modelarts/image_classification",
            "name":"animal",
            "annotated-by":"modelarts/active-learning",
            "confidence": 0.8,
            "creation-time":"2019-01-23 11:30:30"        
        }],
    "inference-loc":"/path/to/inference-output"
}

Image Segmentation

{
    "annotation": [{
        "annotation-format": "PASCAL VOC",
        "type": "modelarts/image_segmentation",
        "annotation-loc": "s3://path/to/annotation/image1.xml",
        "creation-time": "2020-12-16 21:36:27",
        "annotated-by": "human"
    }],
    "usage": "train",
    "source": "s3://path/to/image1.jpg",
    "id": "16d196c19bf61994d7deccafa435398c",
    "sample-type": 0
}

• The parameters such as source, usage, and annotation are the same as those described in Image Classification. For details, see Table 1.
• annotation-loc indicates the path for saving the label file. This parameter is mandatory for image segmentation and object detection but optional for other labeling types.
• annotation-format indicates the format of the label file. This parameter is optional. The default value is PASCAL VOC. Only PASCAL VOC is supported.
• sample-type indicates a sample format. Value 0 indicates image, 1 text, 2 audio, 4 table, and 6 video.

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<annotation>
    <folder>NA</folder>
    <filename>image_0006.jpg</filename>
    <source>
        <database>Unknown</database>
    </source>
    <size>
        <width>230</width>
        <height>300</height>
        <depth>3</depth>
    </size>
    <segmented>1</segmented>
    <mask_source>obs://xianao/out/dataset-8153-Jmf5ylLjRmSacj9KevS/annotation/V001/segmentationClassRaw/image_0006.png</mask_source>
    <object>
        <name>bike</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <mask_color>193,243,53</mask_color>
        <occluded>0</occluded>
        <polygon>
            <x1>71</x1>
            <y1>48</y1>
            <x2>75</x2>
            <y2>73</y2>
            <x3>49</x3>
            <y3>69</y3>
            <x4>68</x4>
            <y4>92</y4>
            <x5>90</x5>
            <y5>101</y5>
            <x6>45</x6>
            <y6>110</y6>
            <x7>71</x7>
            <y7>48</y7>
        </polygon>
    </object>
</annotation>

Text Classification

{
    "source": "content://I like this product ",
    "id":"XGDVGS",
    "annotation": [
        {
            "type": "modelarts/text_classification",
            "name": " positive",
            "annotated-by": "human",
            "creation-time": "2019-01-23 11:30:30"        
        } ]
}

The content parameter indicates the text to be labeled (in UTF-8 encoding format, which can be Chinese). The other parameters are the same as those described in Image Classification. For details, see Table 1.

Named Entity Recognition

{
    "source":"content://Michael Jordan is the most famous basketball player in the world.",
    "usage":"TRAIN",
    "annotation":[
        {
            "type":"modelarts/text_entity",
            "name":"Person",
            "property":{
                "@modelarts:start_index":0,
                "@modelarts:end_index":14
            },
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        },
        {
            "type":"modelarts/text_entity",
            "name":"Category",
            "property":{
                "@modelarts:start_index":34,
                "@modelarts:end_index":44
            },
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        }
    ]
}

The parameters such as source, usage, and annotation are the same as those described in Image Classification. For details, see Table 1.

Table 6 describes the property parameters. For example, if you want to extract Michael from "source":"content://Michael Jordan", the value of start_index is 0 and that of end_index is 7.

Text Triplet

{
    "source":"content://"Three Body" is a series of long science fiction novels created by Liu Cix.",
    "usage":"TRAIN",
    "annotation":[
        {
            "type":"modelarts/text_entity",
            "name":"Person",
            "id":"E1",
            "property":{
                "@modelarts:start_index":67,
                "@modelarts:end_index":74
            },
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        },
        {
            "type":"modelarts/text_entity",
            "name":"Book",
            "id":"E2",
            "property":{
                "@modelarts:start_index":0,
                "@modelarts:end_index":12
            },
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        },
        {
            "type":"modelarts/text_triplet",
            "name":"Author",
            "id":"R1",
            "property":{
                "@modelarts:from":"E1",
                "@modelarts:to":"E2"
            },
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        },
        {
            "type":"modelarts/text_triplet",
            "name":"Works",
            "id":"R2",
            "property":{
                "@modelarts:from":"E2",
                "@modelarts:to":"E1"
            },
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        }
    ]
}

Object Detection

{
    "source":"s3://path/to/image1.jpg",
    "usage":"TRAIN",
    "hard":"true",
    "hard-coefficient":0.8,
    "annotation": [
        {
            "type":"modelarts/object_detection",
            "annotation-loc": "s3://path/to/annotation1.xml",
            "annotation-format":"PASCAL VOC",
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"                
        }]
}

• The parameters such as source, usage, and annotation are the same as those described in Image Classification. For details, see Table 1.
• annotation-loc indicates the path for saving the label file. This parameter is mandatory for object detection and image segmentation but optional for other labeling types.
• annotation-format indicates the format of the label file. This parameter is optional. The default value is PASCAL VOC. Only PASCAL VOC is supported.

<annotation>
   <folder>test_data</folder>
   <filename>260730932.jpg</filename>
   <size>
       <width>767</width>
       <height>959</height>
       <depth>3</depth>
   </size>
   <segmented>0</segmented>
   <object>
       <name>point</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <point>
           <x1>456</x1>
           <y1>596</y1>
       </point>
   </object>
   <object>
       <name>line</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <line>
           <x1>133</x1>
           <y1>651</y1>
           <x2>229</x2>
           <y2>561</y2>
       </line>
   </object>
   <object>
       <name>bag</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <bndbox>
           <xmin>108</xmin>
           <ymin>101</ymin>
           <xmax>251</xmax>
           <ymax>238</ymax>
       </bndbox>
   </object>
   <object>
       <name>boots</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <hard-coefficient>0.8</hard-coefficient>
       <polygon>
           <x1>373</x1>
           <y1>264</y1>
           <x2>500</x2>
           <y2>198</y2>
           <x3>437</x3>
           <y3>76</y3>
           <x4>310</x4>
           <y4>142</y4>
       </polygon>
   </object>
   <object>
       <name>circle</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <circle>
           <cx>405</cx>
           <cy>170</cy>
           <r>100<r>
       </circle>
   </object>
</annotation>

Sound Classification

{
"source":
"s3://path/to/pets.wav", 
    "annotation": [
        {
            "type": "modelarts/audio_classification",
            "name":"cat",    
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        } 
    ]
}

The parameters such as source, usage, and annotation are the same as those described in Image Classification. For details, see Table 1.

Speech Labeling

{
    "source":"s3://path/to/audio1.wav",
    "annotation":[
        {
            "type":"modelarts/audio_content",
            "property":{
                "@modelarts:content":"Today is a good day."
            },
            "annotated-by":"human",
            "creation-time":"2019-01-23 11:30:30"
        }
    ]
}

• The parameters such as source, usage, and annotation are the same as those described in Image Classification. For details, see Table 1.
• The @modelarts:content parameter in property indicates speech content. The data type is String.

Speech Paragraph Labeling

{
    "source":"s3://path/to/audio1.wav",
    "usage":"TRAIN",
    "annotation":[
        {
           
"type":"modelarts/audio_segmentation",
            "property":{
                "@modelarts:start_time":"00:01:10.123",
                "@modelarts:end_time":"00:01:15.456",
               
                "@modelarts:source":"Tom",
               
                "@modelarts:content":"How are you?"
            },
           "annotated-by":"human",
           "creation-time":"2019-01-23 11:30:30"
        },
        {
           "type":"modelarts/audio_segmentation",
            "property":{
                "@modelarts:start_time":"00:01:22.754",
                "@modelarts:end_time":"00:01:24.145",
                "@modelarts:source":"Jerry",
                "@modelarts:content":"I'm fine, thank you."
            },
           "annotated-by":"human",
           "creation-time":"2019-01-23 11:30:30"
        }
    ]
}

• The parameters such as source, usage, and annotation are the same as those described in Image Classification. For details, see Table 1.
• Table 10 describes the property parameters.

  Table 10 property parameters

  Parameter	Data type	Description
  @modelarts:start_time	String	Start time of the sound. The format is hh:mm:ss.SSS. hh indicates the hour, mm indicates the minute, ss indicates the second, and SSS indicates the millisecond.
  @modelarts:end_time	String	End time of the sound. The format is hh:mm:ss.SSS. hh indicates the hour, mm indicates the minute, ss indicates the second, and SSS indicates the millisecond.
  @modelarts:source	String	Sound source
  @modelarts:content	String	Sound content

Video Labeling

{
	"annotation": [{
		"annotation-format": "PASCAL VOC",
		"type": "modelarts/object_detection",
		"annotation-loc": "s3://path/to/annotation1_t1.473722.xml",
		"creation-time": "2020-10-09 14:08:24",
		"annotated-by": "human"
	}],
	"usage": "train",
	"property": {
		"@modelarts:parent_duration": 8,
		"@modelarts:parent_source": "s3://path/to/annotation1.mp4",
		"@modelarts:time_in_video": 1.473722
	},
	"source": "s3://input/path/to/annotation1_t1.473722.jpg",
	"id": "43d88677c1e9a971eeb692a80534b5d5",
	"sample-type": 0
}

• The parameters such as source, usage, and annotation are the same as those described in Image Classification. For details, see Table 1.
• annotation-loc indicates the path for saving the label file. This parameter is mandatory for object detection but optional for other labeling types.
• annotation-format indicates the format of the label file. This parameter is optional. The default value is PASCAL VOC. Only PASCAL VOC is supported.
• sample-type indicates a sample format. Value 0 indicates image, 1 text, 2 audio, 4 table, and 6 video.

<annotation>
   <folder>test_data</folder>
   <filename>260730932_t1.473722.jpg.jpg</filename>
   <size>
       <width>767</width>
       <height>959</height>
       <depth>3</depth>
   </size>
   <segmented>0</segmented>
   <object>
       <name>point</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <point>
           <x1>456</x1>
           <y1>596</y1>
       </point>
   </object>
   <object>
       <name>line</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <line>
           <x1>133</x1>
           <y1>651</y1>
           <x2>229</x2>
           <y2>561</y2>
       </line>
   </object>
   <object>
       <name>bag</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <bndbox>
           <xmin>108</xmin>
           <ymin>101</ymin>
           <xmax>251</xmax>
           <ymax>238</ymax>
       </bndbox>
   </object>
   <object>
       <name>boots</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <hard-coefficient>0.8</hard-coefficient>
       <polygon>
           <x1>373</x1>
           <y1>264</y1>
           <x2>500</x2>
           <y2>198</y2>
           <x3>437</x3>
           <y3>76</y3>
           <x4>310</x4>
           <y4>142</y4>
       </polygon>
   </object>
   <object>
       <name>circle</name>
       <pose>Unspecified</pose>
       <truncated>0</truncated>
       <occluded>0</occluded>
       <difficult>0</difficult>
       <circle>
           <cx>405</cx>
           <cy>170</cy>
           <r>100<r>
       </circle>
   </object>
</annotation>