In this competition, we see a lot of kagglers who are struggling to submit. In fact, I was also facing the same issue. Now, once I have realized how the submission process works, I thought of sharing a notebook that shows how to create an inference kernel properly. \nKernel link is here.
\n\nThis is a simple LGBM model with 7 image stats features. So the model is pretty sub-standard, but the objective of the notebook is to keep everyone on the same page when it comes to submit predictions and get a score.
\n\nThe issue with submission is the following:\nWhen we are committing our kernel, the code would not be able to access the test data, so your model submission would not be prepared. Probably, because hosts do not want us to receive any information from the test data. However, when we submit, then your kernel would access the test data. Now, that is why we need to prepare an if-else statement, so that when we are just committing, sample submission file (or some other file) can be generated in the output and when we are submitting, the intended file would be submitted. Finally, keep the internet off in your inference kernels.
\n\nHappy Kaggling
", "messages": [ { "id": 849046, "postDate": "2020-05-15T13:05:24.817Z", "content": "In this competition, we see a lot of kagglers who are struggling to submit. In fact, I was also facing the same issue. Now, once I have realized how the submission process works, I thought of sharing a notebook that shows how to create an inference kernel properly. \nKernel link is here.
\n\nThis is a simple LGBM model with 7 image stats features. So the model is pretty sub-standard, but the objective of the notebook is to keep everyone on the same page when it comes to submit predictions and get a score.
\n\nThe issue with submission is the following:\nWhen we are committing our kernel, the code would not be able to access the test data, so your model submission would not be prepared. Probably, because hosts do not want us to receive any information from the test data. However, when we submit, then your kernel would access the test data. Now, that is why we need to prepare an if-else statement, so that when we are just committing, sample submission file (or some other file) can be generated in the output and when we are submitting, the intended file would be submitted. Finally, keep the internet off in your inference kernels.
\n\nHappy Kaggling
", "rawMarkdown": "In this competition, we see a lot of kagglers who are struggling to submit. In fact, I was also facing the same issue. Now, once I have realized how the submission process works, I thought of sharing a notebook that shows how to create an inference kernel properly. \nKernel link is [here](https://www.kaggle.com/indranilbhattacharya/image-stats-submission-trial).\n\nThis is a simple LGBM model with 7 image stats features. So the model is pretty sub-standard, but the objective of the notebook is to keep everyone on the same page when it comes to submit predictions and get a score.\n\nThe issue with submission is the following:\nWhen we are committing our kernel, the code would not be able to access the test data, so your model submission would not be prepared. Probably, because hosts do not want us to receive any information from the test data. However, when we submit, then your kernel would access the test data. Now, that is why we need to prepare an if-else statement, so that when we are just committing, sample submission file (or some other file) can be generated in the output and when we are submitting, the intended file would be submitted. Finally, keep the internet off in your inference kernels.\n\nHappy Kaggling", "votes": 2 } ], "comments": [], "raw_markdown_by_id": { "849046": "In this competition, we see a lot of kagglers who are struggling to submit. In fact, I was also facing the same issue. Now, once I have realized how the submission process works, I thought of sharing a notebook that shows how to create an inference kernel properly. \nKernel link is [here](https://www.kaggle.com/indranilbhattacharya/image-stats-submission-trial).\n\nThis is a simple LGBM model with 7 image stats features. So the model is pretty sub-standard, but the objective of the notebook is to keep everyone on the same page when it comes to submit predictions and get a score.\n\nThe issue with submission is the following:\nWhen we are committing our kernel, the code would not be able to access the test data, so your model submission would not be prepared. Probably, because hosts do not want us to receive any information from the test data. However, when we submit, then your kernel would access the test data. Now, that is why we need to prepare an if-else statement, so that when we are just committing, sample submission file (or some other file) can be generated in the output and when we are submitting, the intended file would be submitted. Finally, keep the internet off in your inference kernels.\n\nHappy Kaggling" } }