I want to share my baseline notebooks with you. This is a bare-bones PyTorch solution with no much hyperparameter tuning. I believe you can easily drop the score down a bit with some hyperparameters magic.
\nTried to comment the solution as much as possible to make it useful for beginner ML practitioners.
\nHope you'll find it useful!
", "messages": [ { "id": 1917244, "postDate": "2022-08-28T15:15:44.983Z", "content": "I want to share my baseline notebooks with you. This is a bare-bones PyTorch solution with no much hyperparameter tuning. I believe you can easily drop the score down a bit with some hyperparameters magic.
\nTried to comment the solution as much as possible to make it useful for beginner ML practitioners.
\nHope you'll find it useful!
", "rawMarkdown": "I want to share my baseline notebooks with you. This is a bare-bones PyTorch solution with no much hyperparameter tuning. I believe you can easily drop the score down a bit with some hyperparameters magic. \n\n* Train: [PyTorch-EffNetV2 baseline CV:0.49](https://www.kaggle.com/vslaykovsky/train-pytorch-effnetv2-baseline-cv-0-49)\n* Inference: [PyTorch-EffNetV2 single-model PL:0.49; 5-fold ensemble PL:0.47](https://www.kaggle.com/code/vslaykovsky/infer-pytorch-effnetv2-single-model-pl-0-49) \n\nTried to comment the solution as much as possible to make it useful for beginner ML practitioners. \n\nHope you'll find it useful!", "votes": 39 }, { "id": 1989460, "postDate": "2022-10-16T02:17:07.313Z", "content": "Are you using transfer learning from the pretrained model? It seems that the layers of the effnet model are not frozen.
", "rawMarkdown": "Are you using transfer learning from the pretrained model? It seems that the layers of the effnet model are not frozen.", "votes": 1 }, { "id": 1917924, "postDate": "2022-08-29T06:54:14.683Z", "content": "Thanks for sharing. may I ask how long it took you for tranning and submission?
", "rawMarkdown": "Thanks for sharing. may I ask how long it took you for tranning and submission?", "votes": 1, "replies": [ { "id": 1918302, "postDate": "2022-08-29T13:30:04.953Z", "content": "Training locally on a laptop approx 4 hours. But a single model training is just around 1hour on a 3080 laptop. Submission is approx 3-7 hours, depends on the number of models to use
", "rawMarkdown": "Training locally on a laptop approx 4 hours. But a single model training is just around 1hour on a 3080 laptop. Submission is approx 3-7 hours, depends on the number of models to use", "votes": 2 }, { "id": 1918319, "postDate": "2022-08-29T13:46:33.877Z", "content": "Very helpful, thanks again.
", "rawMarkdown": "Very helpful, thanks again.", "votes": 1 }, { "id": 1939085, "postDate": "2022-09-14T14:18:39.033Z", "content": "How much time did it take for a single epoch ?
", "rawMarkdown": "How much time did it take for a single epoch ?" } ] }, { "id": 1917361, "postDate": "2022-08-28T16:57:31.297Z", "content": "Does your \"single model\" means 1 fold or 5-folds combined?
", "rawMarkdown": "Does your \"single model\" means 1 fold or 5-folds combined?", "votes": 1, "replies": [ { "id": 1917375, "postDate": "2022-08-28T17:11:15.337Z", "content": "Single model is a model that is trained on all train data folds. It is stored as 'effnetv2' in the training notebook. 5 models for each of 5 folds are also trained mainly for CV score.
", "rawMarkdown": "Single model is a model that is trained on all train data folds. It is stored as 'effnetv2' in the training notebook. 5 models for each of 5 folds are also trained mainly for CV score. " }, { "id": 1917693, "postDate": "2022-08-29T01:39:29.170Z", "content": "my forked submission timeout.
", "rawMarkdown": "my forked submission timeout.", "votes": 1 }, { "id": 1917896, "postDate": "2022-08-29T06:37:05.467Z", "content": "Hi. This is because MODEL_NAMES was set to all models. Try to use the single model in MODEL_NAMES
", "rawMarkdown": "Hi. This is because MODEL_NAMES was set to all models. Try to use the single model in MODEL_NAMES" } ] }, { "id": 1917369, "postDate": "2022-08-28T17:05:03.513Z", "content": "Nice & Clean baseline. Thanks for sharing to the community.
", "rawMarkdown": "Nice & Clean baseline. Thanks for sharing to the community.", "votes": 2 }, { "id": 1985137, "postDate": "2022-10-13T06:02:49.800Z", "content": "Thanks for sharing. these codes are useful for me, but i got some trouble.
\n When i run the code of train using GPU model, i got this error: AttributeError: module 'torchvision.models.efficientnet' has no attribute 'EfficientNet_V2_S_Weights'. Could you tell me how can i solve it? Thanks in advance.
Hi. Make sure that the right version of Pytorch is install via pip install ... .whl command
great work! thanks for sharing
", "rawMarkdown": "great work! thanks for sharing", "votes": 1 } ], "comments": [ { "id": 1989460, "author_name": "Pierre Tisseur", "author_url": "", "post_date": "2022-10-16T02:17:07.313000", "content": "Are you using transfer learning from the pretrained model? It seems that the layers of the effnet model are not frozen.
", "votes": 1, "replies": [] }, { "id": 1917924, "author_name": "Mengfei Li", "author_url": "", "post_date": "2022-08-29T06:54:14.683000", "content": "Thanks for sharing. may I ask how long it took you for tranning and submission?
", "votes": 1, "replies": [ { "id": 1918302, "author_name": "Vladimir Slaykovskiy", "author_url": "", "post_date": "2022-08-29T13:30:04.953000", "content": "Training locally on a laptop approx 4 hours. But a single model training is just around 1hour on a 3080 laptop. Submission is approx 3-7 hours, depends on the number of models to use
", "votes": 2, "replies": [] }, { "id": 1918319, "author_name": "Mengfei Li", "author_url": "", "post_date": "2022-08-29T13:46:33.877000", "content": "Very helpful, thanks again.
", "votes": 1, "replies": [] }, { "id": 1939085, "author_name": "Mithil Salunkhe", "author_url": "", "post_date": "2022-09-14T14:18:39.033000", "content": "How much time did it take for a single epoch ?
", "votes": 0, "replies": [] } ] }, { "id": 1917361, "author_name": "Harshit Sheoran", "author_url": "", "post_date": "2022-08-28T16:57:31.297000", "content": "Does your \"single model\" means 1 fold or 5-folds combined?
", "votes": 1, "replies": [ { "id": 1917375, "author_name": "Vladimir Slaykovskiy", "author_url": "", "post_date": "2022-08-28T17:11:15.337000", "content": "Single model is a model that is trained on all train data folds. It is stored as 'effnetv2' in the training notebook. 5 models for each of 5 folds are also trained mainly for CV score.
", "votes": 0, "replies": [] }, { "id": 1917693, "author_name": "dragon zhang", "author_url": "", "post_date": "2022-08-29T01:39:29.170000", "content": "my forked submission timeout.
", "votes": 1, "replies": [] }, { "id": 1917896, "author_name": "Vladimir Slaykovskiy", "author_url": "", "post_date": "2022-08-29T06:37:05.467000", "content": "Hi. This is because MODEL_NAMES was set to all models. Try to use the single model in MODEL_NAMES
", "votes": 0, "replies": [] } ] }, { "id": 1917369, "author_name": "Nischay Dhankhar", "author_url": "", "post_date": "2022-08-28T17:05:03.513000", "content": "Nice & Clean baseline. Thanks for sharing to the community.
", "votes": 2, "replies": [] }, { "id": 1985137, "author_name": "Zhuolin Zhang", "author_url": "", "post_date": "2022-10-13T06:02:49.800000", "content": "Thanks for sharing. these codes are useful for me, but i got some trouble.
\n When i run the code of train using GPU model, i got this error: AttributeError: module 'torchvision.models.efficientnet' has no attribute 'EfficientNet_V2_S_Weights'. Could you tell me how can i solve it? Thanks in advance.
Hi. Make sure that the right version of Pytorch is install via pip install ... .whl command
great work! thanks for sharing
", "votes": 1, "replies": [] } ], "raw_markdown_by_id": { "1917244": "I want to share my baseline notebooks with you. This is a bare-bones PyTorch solution with no much hyperparameter tuning. I believe you can easily drop the score down a bit with some hyperparameters magic. \n\n* Train: [PyTorch-EffNetV2 baseline CV:0.49](https://www.kaggle.com/vslaykovsky/train-pytorch-effnetv2-baseline-cv-0-49)\n* Inference: [PyTorch-EffNetV2 single-model PL:0.49; 5-fold ensemble PL:0.47](https://www.kaggle.com/code/vslaykovsky/infer-pytorch-effnetv2-single-model-pl-0-49) \n\nTried to comment the solution as much as possible to make it useful for beginner ML practitioners. \n\nHope you'll find it useful!", "1989460": "Are you using transfer learning from the pretrained model? It seems that the layers of the effnet model are not frozen.", "1917924": "Thanks for sharing. may I ask how long it took you for tranning and submission?", "1917361": "Does your \"single model\" means 1 fold or 5-folds combined?", "1917369": "Nice & Clean baseline. Thanks for sharing to the community.", "1985137": "Thanks for sharing. these codes are useful for me, but i got some trouble. \n When i run the code of train using GPU model, i got this error: AttributeError: module 'torchvision.models.efficientnet' has no attribute 'EfficientNet_V2_S_Weights'. Could you tell me how can i solve it? Thanks in advance.", "1917303": "great work! thanks for sharing" } }