| {"node":{"id":"urn:cid:bafkr4ieew2ui4vcemfibfbv4csgykzf7bz3pk3gmx3zdahupph7tv26jfm","properties":{"dataRegistrationJcs":"urn:cid:baga6yaq6eck5l2xjlngsomwfos67jz2ohieh344zqru3xvunibf2trxiuqyea","nodeType":"data","registeredBy":"did:key:z6MkhQD1A9eMQ8bZNGmBiCVz7kG4mfnApD7WjHKNhkZp7HEY","timestamp":"2024-01-29T16:00:24Z"}},"enrichments":{"asset_hub":{"asset_id":103,"asset_name":"VGG-19","owning_project":"ImageNet Challenge 2014","asset_description":"VGG-19 is a convolutional neural network that is 19 layers deep. It was developed by Karen Simonyan and Andrew Zisserman. The model is notable for its depth and the use of very small (3x3) convolution filters. VGG-19 achieved significant improvements in accuracy in large-scale image recognition by increasing network depth. It was part of the ImageNet Challenge 2014 submission, where it performed exceptionally well in the localisation and classification tracks. The pretrained network is capable of classifying images into 1000 categories and is widely used for various computer vision tasks.","asset_format":"PyTorch","asset_type":"Model","asset_blob_type":"","source_location_url":"","contact_info":"Refer to the original paper or the PyTorch official channels for contact information.","license":"Refer to the PyTorch repository for licensing information.","license_link":"","registered_date":"2024-01-29T16:00:32.203438Z","last_modified_date":"2024-01-29T16:00:32.203438Z"}}} |