I have used timm(to include much effective models).I did ensembling of dla102,gluon_resnext101_32x4d,dla102x which gave me private score of 0.451940 and public score 0.44787.I am sharing my colab notebook of all the 3 models.
\n\ndla102 model\ndla 102x model\ngluon_resnext101_32x4d model
\n\n\n\nThe attached submission (6).csv is collection of all the outputs from different trained models and a.csv is the final ensembled output.
", "comments": [], "comment_count": 0, "messages": [ { "id": 743667, "postDate": "2020-02-12T07:11:44.980Z", "content": "I have used timm(to include much effective models).I did ensembling of dla102,gluon_resnext101_32x4d,dla102x which gave me private score of 0.451940 and public score 0.44787.I am sharing my colab notebook of all the 3 models.
\n\ndla102 model\ndla 102x model\ngluon_resnext101_32x4d model
\n\n\n\nThe attached submission (6).csv is collection of all the outputs from different trained models and a.csv is the final ensembled output.
", "rawMarkdown": "I have used timm(to include much effective models).I did ensembling of dla102,gluon_resnext101_32x4d,dla102x which gave me private score of 0.451940 and public score 0.44787.I am sharing my colab notebook of all the 3 models.\n\n[dla102 model](https://colab.research.google.com/drive/1FrFF-Mtd-AA8KsLYp7E-eGFffDpj7Vtb)\n[dla 102x model](https://colab.research.google.com/drive/1b06RaGvGUPzaVfxhLwJYX0zEW5HD9OIH)\n[gluon_resnext101_32x4d model](https://colab.research.google.com/drive/19hEhd_LRZQgV5tjZkeX1E90P2yTJhL_x)\n\n[Ensembler model](https://colab.research.google.com/drive/1TcTM3DSWs4mjxjgLP-RI9ium8EfkukqT)\n\nThe attached submission (6).csv is collection of all the outputs from different trained models and a.csv is the final ensembled output.\n\n\n \n\n" } ], "complete": true, "source": "live", "fetched_at": "2026-10-20T05:03:41Z", "competition_id": 18191, "competition_slug": "cl-cv2020", "team_id": 4344278, "solution_url": "/competitions/cl-cv2020/writeups/tg1234yfy-3rd-position" }