{"__v":1,"_id":"57900595502bcf1700e9bbea","category":{"project":"574723d2c333472000a7196f","version":"574723d2c333472000a71972","_id":"574723d2c333472000a71973","__v":0,"sync":{"url":"","isSync":false},"reference":false,"createdAt":"2016-05-26T16:26:58.319Z","from_sync":false,"order":0,"slug":"documentation","title":"Documentation"},"parentDoc":null,"project":"574723d2c333472000a7196f","user":"5747236363c8230e003aa9ec","version":{"__v":6,"_id":"574723d2c333472000a71972","project":"574723d2c333472000a7196f","createdAt":"2016-05-26T16:26:58.290Z","releaseDate":"2016-05-26T16:26:58.290Z","categories":["574723d2c333472000a71973","579c1f017a6aaa0e00756117","579c39a7f3f4d50e00b54784","579c39a9cbe2390e00c25e2b","579c39afc6625a0e00a887c8","579c3a87cbe2390e00c25e2c"],"is_deprecated":false,"is_hidden":false,"is_beta":false,"is_stable":true,"codename":"","version_clean":"1.0.0","version":"1.0"},"updates":[],"next":{"pages":[],"description":""},"createdAt":"2016-07-20T23:13:25.025Z","link_external":false,"link_url":"","githubsync":"","sync_unique":"","hidden":false,"api":{"results":{"codes":[]},"settings":"","auth":"required","params":[],"url":""},"isReference":false,"order":1,"body":"[block:api-header]\n{\n  \"type\": \"basic\",\n  \"title\": \"Classify Images or S3 Folders\"\n}\n[/block]\nYou have the option of providing your own images or folders in your corresponding customer bucket on S3. Here are some things to consider:\n[block:parameters]\n{\n  \"data\": {\n    \"h-0\": \"Image URLs\",\n    \"h-1\": \"Image Data\",\n    \"h-2\": \"S3 Folders\",\n    \"0-0\": \"Fast and easy to use\",\n    \"1-0\": \"Data can be stored anywhere\",\n    \"0-1\": \"Takes time to upload\",\n    \"1-1\": \"Good for running tests locally\",\n    \"0-2\": \"Fastest option since our algorithms are hosted on AWS\",\n    \"1-2\": \"Good for large amounts of data\"\n  },\n  \"cols\": 3,\n  \"rows\": 2\n}\n[/block]\nIn short, URLs are easy to get started with while providing flexibility on data storage, while S3 folders are better long-term performance and maintenance wise.\n\nBonus: If email notifications are set up on your dashboard, you will receive an email with a CSV report on the classification results.\n[block:api-header]\n{\n  \"type\": \"post\",\n  \"title\": \"Classify Image URLs\"\n}\n[/block]\n\n[block:code]\n{\n  \"codes\": [\n    {\n      \"code\": \"curl -H 'X-ApiKey: YOUR_API_KEY' -X POST -d \\\"image_urls[]=https://s3.amazonaws.com/semanticmd-public/dcm_test/IM-0001-0001.dcm\\\" -d \\\"image_urls[]=https://s3.amazonaws.com/semanticmd-public/dcm_test/IM-0001-0002.dcm\\\" https://api-testing.semantic.md/v1/image/classify/YOUR_CLASSIFIER_ID\",\n      \"language\": \"curl\"\n    }\n  ]\n}\n[/block]\nWhat’s actually happening:\n\n  * SemanticMD pulls the data from your URLs.\n  * Data is passed to the deep learning model with the given ID.\n  * Returns a job ID that can be polled until results are available.\n\nYou can find your secret API key on your [dashboard](http://app.semantic.md).","excerpt":"","slug":"how-to-start-classifying-images","type":"basic","title":"Image Classification"}

Image Classification


[block:api-header] { "type": "basic", "title": "Classify Images or S3 Folders" } [/block] You have the option of providing your own images or folders in your corresponding customer bucket on S3. Here are some things to consider: [block:parameters] { "data": { "h-0": "Image URLs", "h-1": "Image Data", "h-2": "S3 Folders", "0-0": "Fast and easy to use", "1-0": "Data can be stored anywhere", "0-1": "Takes time to upload", "1-1": "Good for running tests locally", "0-2": "Fastest option since our algorithms are hosted on AWS", "1-2": "Good for large amounts of data" }, "cols": 3, "rows": 2 } [/block] In short, URLs are easy to get started with while providing flexibility on data storage, while S3 folders are better long-term performance and maintenance wise. Bonus: If email notifications are set up on your dashboard, you will receive an email with a CSV report on the classification results. [block:api-header] { "type": "post", "title": "Classify Image URLs" } [/block] [block:code] { "codes": [ { "code": "curl -H 'X-ApiKey: YOUR_API_KEY' -X POST -d \"image_urls[]=https://s3.amazonaws.com/semanticmd-public/dcm_test/IM-0001-0001.dcm\" -d \"image_urls[]=https://s3.amazonaws.com/semanticmd-public/dcm_test/IM-0001-0002.dcm\" https://api-testing.semantic.md/v1/image/classify/YOUR_CLASSIFIER_ID", "language": "curl" } ] } [/block] What’s actually happening: * SemanticMD pulls the data from your URLs. * Data is passed to the deep learning model with the given ID. * Returns a job ID that can be polled until results are available. You can find your secret API key on your [dashboard](http://app.semantic.md).