![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16761666%2F53a8c0d183437b30003dfe780add995a%2FIMG_0756.jpeg?generation=1698245486096252&alt=media\")
maybe I just need this…Why I got “threw exception” erorr while doing multi-img-size ensembel？QAQ😭
\nhttps://www.kaggle.com/code/seeingtimes/threw-exception-error/notebook?scriptVersionId=147158439
\nlog：
\nSuccessfully ran in 33.6s
\nAccelerator
\nGPU P100
Environment
\nLatest Container Image
Output
\n21 B
Time
\n#
\nLog Message
\n10.7s 1 /opt/conda/lib/python3.10/site-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.5\n10.7s 2 warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"
\n13.7s 3 /opt/conda/lib/python3.10/site-packages/sklearn/base.py:318: UserWarning: Trying to unpickle estimator LabelEncoder from version 1.3.0 when using version 1.2.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
\n13.7s 4 https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
\n13.7s 5 warnings.warn(
\n17.0s 6 Test_768: 0%| | 0/1 [00:00<?, ?it/s]
\n23.7s 7 Test_1024: 0%| | 0/1 [00:00<?, ?it/s]\u001b[ATest_768: 100%|██████████| 1/1 [00:06<00:00, 6.53s/it]Test_768: 100%|██████████| 1/1 [00:06<00:00, 6.53s/it]
\n27.2s 8
\n27.2s 9 Test_1024: 100%|██████████| 1/1 [00:10<00:00, 10.18s/it]\u001b[ATest_1024: 100%|██████████| 1/1 [00:10<00:00, 10.19s/it]
\n31.1s 10 /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass --Exporter.preprocessors item … multiple times to add items to a list.
\n31.1s 11 warn(
\n31.1s 12 [NbConvertApp] WARNING | Config option kernel_spec_manager_class not recognized by NbConvertApp.
\n31.1s 13 [NbConvertApp] Converting notebook notebook.ipynb to notebook
\n31.4s 14 [NbConvertApp] Writing 30362 bytes to notebook.ipynb
\n32.7s 15 /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass --Exporter.preprocessors item … multiple times to add items to a list.
\n32.7s 16 warn(
\n32.7s 17 [NbConvertApp] WARNING | Config option kernel_spec_manager_class not recognized by NbConvertApp.
\n32.8s 18 [NbConvertApp] Converting notebook notebook.ipynb to html
\n33.5s 19 [NbConvertApp] Writing 336373 bytes to results.html
Why I got “threw exception” erorr while doing multi-img-size ensembel？QAQ😭
\nhttps://www.kaggle.com/code/seeingtimes/threw-exception-error/notebook?scriptVersionId=147158439
\nlog：
\nSuccessfully ran in 33.6s
\nAccelerator
\nGPU P100
Environment
\nLatest Container Image
Output
\n21 B
Time
\n#
\nLog Message
\n10.7s 1 /opt/conda/lib/python3.10/site-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.5\n10.7s 2 warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"
\n13.7s 3 /opt/conda/lib/python3.10/site-packages/sklearn/base.py:318: UserWarning: Trying to unpickle estimator LabelEncoder from version 1.3.0 when using version 1.2.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
\n13.7s 4 https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
\n13.7s 5 warnings.warn(
\n17.0s 6 Test_768: 0%| | 0/1 [00:00<?, ?it/s]
\n23.7s 7 Test_1024: 0%| | 0/1 [00:00<?, ?it/s]\u001b[ATest_768: 100%|██████████| 1/1 [00:06<00:00, 6.53s/it]Test_768: 100%|██████████| 1/1 [00:06<00:00, 6.53s/it]
\n27.2s 8
\n27.2s 9 Test_1024: 100%|██████████| 1/1 [00:10<00:00, 10.18s/it]\u001b[ATest_1024: 100%|██████████| 1/1 [00:10<00:00, 10.19s/it]
\n31.1s 10 /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass --Exporter.preprocessors item … multiple times to add items to a list.
\n31.1s 11 warn(
\n31.1s 12 [NbConvertApp] WARNING | Config option kernel_spec_manager_class not recognized by NbConvertApp.
\n31.1s 13 [NbConvertApp] Converting notebook notebook.ipynb to notebook
\n31.4s 14 [NbConvertApp] Writing 30362 bytes to notebook.ipynb
\n32.7s 15 /opt/conda/lib/python3.10/site-packages/traitlets/traitlets.py:2930: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass --Exporter.preprocessors item … multiple times to add items to a list.
\n32.7s 16 warn(
\n32.7s 17 [NbConvertApp] WARNING | Config option kernel_spec_manager_class not recognized by NbConvertApp.
\n32.8s 18 [NbConvertApp] Converting notebook notebook.ipynb to html
\n33.5s 19 [NbConvertApp] Writing 336373 bytes to results.html
It is the first year in college so I ability is limited.
", "rawMarkdown": "It is the first year in college so I ability is limited.", "replies": [ { "id": 2490926, "postDate": "2023-10-21T07:48:21.463Z", "content": "I tried to predict the train set locally and it worked perfectly， it's probably because their hardware is not strong enough. It is excellent you are in the first year and got 37th LB in this competition at this moment，if you are interest to work together with my team， that would be great！ I have teammate study in Tsinghua university and he is also from
\nAnhui！
Emmmmm……I really want to know how you work it out know because I submitted 5 submissions
\nbut nearly all of them returned “threw exception”.And I noticed this https://www.kaggle.com/code/yukkyo/probing-all-test-sample-have-thumbnail,it really confused me.
maybe I just need this…
I tried to crop every image into 128*128 for training.In order to save time I try to dropout some of them in random when I submission it,
\nbut after 8 hours I get the same error as well. I think it's because I am so lucky that my model dropout every image,so there nothing in the prediction.But I can't make sure,the only thing I know is that when I add a count to make sure every prediction is based on at lest 25 small images,there is no error at all.
It is the first year in college so I ability is limited.
", "votes": 0, "replies": [ { "id": 2490926, "author_name": "Seeing Times", "author_url": "", "post_date": "2023-10-21T07:48:21.463000", "content": "I tried to predict the train set locally and it worked perfectly， it's probably because their hardware is not strong enough. It is excellent you are in the first year and got 37th LB in this competition at this moment，if you are interest to work together with my team， that would be great！ I have teammate study in Tsinghua university and he is also from
\nAnhui！
Emmmmm……I really want to know how you work it out know because I submitted 5 submissions
\nbut nearly all of them returned “threw exception”.And I noticed this https://www.kaggle.com/code/yukkyo/probing-all-test-sample-have-thumbnail,it really confused me.
maybe I just need this…