Platform For AI:End-to-end text recognition

Invoke PAI commands using the SQL Script component, MaxCompute client, or ODPS SQL node in DataWorks. For more information, see Connect using local client (odpscmd) or Develop an ODPS SQL task.

pai -name ev_predict_ext
             -Dmodel_path='Path to model'
             -Dmodel_type='text_spotter'
             -Dinput_oss_file='oss://path/to/filelist.txt'
             -Doutput_oss_file='oss://path/to/result.txt'
             -Dimage_type='url'
             -Dnum_worker=2
             -DcpuRequired=800
             -DgpuRequired=100
             -Dbuckets='OSS buckets'
             -Darn='RoleArn'
             -DossHost='OSS domain name'

See Parameters for parameter descriptions.

Each line contains an image path and prediction result in JSON format.

oss://path/to/your/image1.jpg,  JSON result string
oss://path/to/your/image2.jpg,  JSON result string
oss://path/to/your/image3.jpg,  JSON result string

Result structure:

{
  "detection_keypoints": [[[243.57516479492188, 198.84210205078125], [243.91038513183594, 247.62425231933594], [385.5513916015625, 246.61660766601562], [385.2197570800781, 197.79345703125]], [[292.2718200683594, 114.44700622558594], [292.2237243652344, 164.684814453125], [571.1962890625, 164.931640625], [571.2444458007812, 114.67433166503906]]],
  "detection_boxes": [[243.5308074951172, 197.69570922851562, 385.59625244140625, 247.7247772216797], [292.1929931640625, 114.28043365478516, 571.2748413085938, 165.09771728515625]],
  "detection_scores": [0.9942291975021362, 0.9940272569656372],
  "detection_classes": [1, 1],
  "detection_classe_names": ["text", "text"],
  "detection_texts_ids" : [[1,2,2008,12], [1,2,2008,12]],
  "detection_texts": ["This is an example", "This is an example"],
  "detection_texts_scores" : [0.88, 0.88]
 }

Output parameters:

Parameter	Description	Shape	Data type
detection_boxes	Bounding box coordinates in [top, left, bottom, right] format	[num_detections, 4]	FLOAT
detection_scores	Detection confidence score	num_detections	FLOAT
detection_classes	Detection category ID	num_detections	INT
detection_class_names	Detection category name	num_detections	STRING
detection_keypoints	Four corner points in (y,x) coordinate format	[num_detections, 4, 2]	FLOAT
detection_texts_ids	Character ID array for recognized text	[num_detections, max_text_length]	INT
detection_texts	Recognized text content	[num_detections]	STRING
detection_texts_scores	Recognition confidence score	[num_detections]	FLOAT