Golang Sample | Python Sample | Node.js Sample |
---|---|---|
We're classifying images into NSFW and SFW categories.
Following are the image categories we classify into NSFW categories.
- Porn
- Explicit Nudity
- Animated Porn
- Suggestive Nudity
- Gore
- Get your API key by signing up on app.nanonets.com
curl --request POST --url 'https://app.nanonets.com/api/v2/ImageCategorization/LabelUrls/' --header 'accept: application/x-www-form-urlencoded' -d 'modelId=7390a500-9fe1-483b-8123-750b96fc660c&urls=https://goo.gl/ICoiHc' -u '-REPLCAE_YOUR_API_KEY:'
#REPLACE YOUR API KEY
import requests
url = 'https://app.nanonets.com/api/v2/ImageCategorization/LabelUrls/'
headers = {
'accept': 'application/x-www-form-urlencoded'
}
data = {'modelId': '7390a500-9fe1-483b-8123-750b96fc660c', 'urls' : ['https://goo.gl/ICoiHc']}
response = requests.request('POST', url, headers=headers, auth=requests.auth.HTTPBasicAuth('REPLACE_YOUR_API_KEY', ''), data=data)
print(response.text)
var request = require("request");
var options = { method: 'POST',
url: 'http://app.nanonets.com/api/v2/ImageCategorization/LabelUrls/',
headers:
{ 'cache-control': 'no-cache',
Authorization: 'Basic ' + new Buffer('REPLACE YOUR API KEY' + ":" + '').toString("base64"),
'Content-Type': 'application/x-www-form-urlencoded' },
form:
{ urls: 'https://goo.gl/ICoiHc',
modelId: '7390a500-9fe1-483b-8123-750b96fc660c' } };
request(options, function (error, response,body) {
if (error) throw new Error(error);
console.log(body);
});
git clone https://github.com/NanoNets/nsfw-api
cd nsfw-api
Get your free API Key from http://app.nanonets.com/#/keys
export NANONETS_API_KEY=YOUR_API_KEY_GOES_HERE
python ./code/create_model.py
_Note: This generates a MODEL_ID that you need for the next step
export NANONETS_MODEL_ID=YOUR_MODEL_ID
_Note: you will get YOUR_MODEL_ID from the previous step
The training data is found in images
(image files) and annotations
(annotations for the image files)
python ./code/upload_training.py
Once the Images have been uploaded, begin training the Model
python ./code/train_model.py
The model takes ~2 hours to train. You will get an email once the model is trained. In the meanwhile you check the state of the model
python ./code/model_state.py
Once the model is trained. You can make predictions using the model
python ./code/prediction.py PATH_TO_YOUR_IMAGE.jpg
Sample Usage:
python ./code/prediction.py ./multilabel_data/ImageSets/2795.jpg