Please join me in congratulating our TPU Stars, awarded to the most knowledgeable and helpful TPU experts in this competition.
\n✨ Dimitre Oliveira is now a multiple-time TPU Star award winner. He made tremendous contributions with his TPU expertise to this competition across discussions, dataset (TFRecords) creation, generating data with GANs, & training + inference using multiple approaches. These high quality and easy-to-follow instructive notebooks provide a critical starting point for many to learn with TPUs. Check out his notebooks:
\n✨ Abhinand created the widely-popular Vision Transformer(ViT): Tutorial + Baseline, this competition's most upvoted TPU notebook. It provided an informative and welcoming introduction to vision transformers and a helpful baseline model.
\n✨ Heroseo authored [CNN or Transformer]Pytorch XLA(TPU) for Cassava, a fantastic Data-efficient Image Transformer (DeIT) starter using PyTorch XLA, which. He also shared a How-to on Fine-tuning as well as Learning with Noisy Labels, all tremendous PyTorch XLA on TPU resources. His notebooks provide much-desired PyTorch on TPU expertise and also do a nice job of showing how TPUs & GPUs can work together.
All of these stars will be receiving the monetary prize with this award. Thank you so much for your valuable contributions to the competition and Kaggle broadly!
", "messages": [ { "id": "1253505", "postDate": "03/26/2021 19:58:04", "content": "Please join me in congratulating our TPU Stars, awarded to the most knowledgeable and helpful TPU experts in this competition.
\n✨ Dimitre Oliveira is now a multiple-time TPU Star award winner. He made tremendous contributions with his TPU expertise to this competition across discussions, dataset (TFRecords) creation, generating data with GANs, & training + inference using multiple approaches. These high quality and easy-to-follow instructive notebooks provide a critical starting point for many to learn with TPUs. Check out his notebooks:
\n✨ Abhinand created the widely-popular Vision Transformer(ViT): Tutorial + Baseline, this competition's most upvoted TPU notebook. It provided an informative and welcoming introduction to vision transformers and a helpful baseline model.
\n✨ Heroseo authored [CNN or Transformer]Pytorch XLA(TPU) for Cassava, a fantastic Data-efficient Image Transformer (DeIT) starter using PyTorch XLA, which. He also shared a How-to on Fine-tuning as well as Learning with Noisy Labels, all tremendous PyTorch XLA on TPU resources. His notebooks provide much-desired PyTorch on TPU expertise and also do a nice job of showing how TPUs & GPUs can work together.
All of these stars will be receiving the monetary prize with this award. Thank you so much for your valuable contributions to the competition and Kaggle broadly!
", "rawMarkdown": "Please join me in congratulating our [TPU Stars](https://www.kaggle.com/tpu-stars), awarded to the [most knowledgeable and helpful TPU experts](https://www.kaggle.com/c/cassava-leaf-disease-classification/overview/prizes) in this competition.\n\n✨ [Dimitre Oliveira](https://www.kaggle.com/dimitreoliveira) is now a multiple-time TPU Star award winner. He made tremendous contributions with his TPU expertise to this competition across discussions, dataset (TFRecords) creation, generating data with GANs, & training + inference using multiple approaches. These high quality and easy-to-follow instructive notebooks provide a critical starting point for many to learn with TPUs. Check out his notebooks:\n- [Creating Stratified TFRecords 256x256](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-stratified-tfrecords-256x256)\n- [Tensorflow TPU Training](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-tpu-tensorflow-training) + [Inference](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-tpu-tensorflow-inference)\n- [Supervised Contrastive Learning Overview/Training](https://www.kaggle.com/dimitreoliveira/cassava-leaf-supervised-contrastive-learning) + [Inference](https://www.kaggle.com/dimitreoliveira/cassava-supervised-contrastive-learning-inference)\n- [CycleGAN Data Augmentation](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-cyclegan-data-augmentation)\n- [Training with TPU v2 Pods](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-training-with-tpu-v2-pods)\n\n✨ [Abhinand](https://www.kaggle.com/abhinand05) created the widely-popular [Vision Transformer(ViT): Tutorial + Baseline](https://www.kaggle.com/abhinand05/vision-transformer-vit-tutorial-baseline), this competition's most upvoted TPU notebook. It provided an informative and welcoming introduction to vision transformers and a helpful baseline model.\n✨ [Heroseo](https://www.kaggle.com/piantic) authored [[CNN or Transformer]Pytorch XLA(TPU) for Cassava](https://www.kaggle.com/piantic/cnn-or-transformer-pytorch-xla-tpu-for-cassava), a fantastic Data-efficient Image Transformer (DeIT) starter using PyTorch XLA, which. He also shared a [How-to on Fine-tuning](https://www.kaggle.com/piantic/how-to-finetuning-models-pytorch-xla-tpu) as well as [Learning with Noisy Labels](https://www.kaggle.com/piantic/learning-with-noisy-labels-pytorch-xla-tpu), all tremendous PyTorch XLA on TPU resources. His notebooks provide much-desired PyTorch on TPU expertise and also do a nice job of showing how TPUs & GPUs can work together.\n\nAll of these stars will be receiving the monetary prize with this award. Thank you so much for your valuable contributions to the competition and Kaggle broadly!", "votes": null }, { "id": "1253798", "postDate": "03/27/2021 03:36:19", "content": "Congratulations to the wonderful contributors. This is very nice! I hope to learn a lot from these kernels.
", "rawMarkdown": "Congratulations to the wonderful contributors. This is very nice! I hope to learn a lot from these kernels.", "votes": null }, { "id": "1254253", "postDate": "03/27/2021 13:26:43", "content": "I would like to thanks the Kaggle team and the community for receiving so well my work here, this competition was special for me, I got to make a lot of experiments and publish some of them here with the community. Congratulations to @abhinand05 and @piantic for winning as well.
\nFor anyone else that wants to look in some of the other experiments checkout the GitHub repository, I created for this competition.
", "rawMarkdown": "I would like to thanks the Kaggle team and the community for receiving so well my work here, this competition was special for me, I got to make a lot of experiments and publish some of them here with the community. Congratulations to @abhinand05 and @piantic for winning as well.\n\nFor anyone else that wants to look in some of the other experiments checkout the [GitHub](https://github.com/dimitreOliveira/Cassava-Leaf-Disease-Classification) repository, I created for this competition.", "votes": null }, { "id": "1254302", "postDate": "03/27/2021 14:07:20", "content": "I would like to thank the organizer and the Kaggle team for their efforts to ensure the successful competition. Also thanks to the other kagglers who enjoyed my notebooks and discussions I shared during the competition.
\nI will continue to share good notebooks and discussions in the community. I hope to see all in other competitions.
\np.s. Congratulation on TPU Star award as wall @dimitreoliveira, @abhinand05.
Thank you!
", "rawMarkdown": "I would like to thank the organizer and the Kaggle team for their efforts to ensure the successful competition. Also thanks to the other kagglers who enjoyed my notebooks and discussions I shared during the competition. \n\nI will continue to share good notebooks and discussions in the community. I hope to see all in other competitions. \np.s. Congratulation on TPU Star award as wall @dimitreoliveira, @abhinand05.\n\nThank you!", "votes": null }, { "id": "1254332", "postDate": "03/27/2021 14:43:24", "content": "Many thanks to Kaggle Team for awarding my work. Looking forward to contributing more to the community. Happy Kaggling! Congrats to @dimitreoliveira and @piantic as well!
", "rawMarkdown": "Many thanks to Kaggle Team for awarding my work. Looking forward to contributing more to the community. Happy Kaggling! Congrats to @dimitreoliveira and @piantic as well!", "votes": null }, { "id": "1254703", "postDate": "03/28/2021 01:51:42", "content": "Congratulations!
\nI believe that all of you deserve the awards. Before I started the cassava competition, I knew only the basics about image classification, but I have learned a lot from your valuable kernels. What I learned from the notebooks was even greater than the competition medal. Thank you very much!
Congratulations TPU stars! @dimitreoliveira @abhinand05 @piantic Thanks for sharing!
", "rawMarkdown": "Congratulations TPU stars! @dimitreoliveira @abhinand05 @piantic Thanks for sharing!", "votes": null }, { "id": "1255211", "postDate": "03/28/2021 15:14:11", "content": "Excellent job @dimitreoliveira! I think that this kind of work will help a lot the community, and for sure, I will take a look more deeply into your works to inspire and try to do some stuff with TPUs. Muito bom meu velho! 😄🔥💥
", "rawMarkdown": "Excellent job @dimitreoliveira! I think that this kind of work will help a lot the community, and for sure, I will take a look more deeply into your works to inspire and try to do some stuff with TPUs. Muito bom meu velho! 😄🔥💥", "votes": null }, { "id": "1255414", "postDate": "03/28/2021 19:19:32", "content": "Thanks @rapela , I also think that this work is great for the community, um abraco!
", "rawMarkdown": "Thanks @rapela , I also think that this work is great for the community, um abraco!", "votes": null }, { "id": "1261282", "postDate": "04/02/2021 22:03:16", "content": "Congratulations, @dimitreoliveira, @abhinand05 and @piantic! And thanks for sharing your notebooks!
", "rawMarkdown": "Congratulations, @dimitreoliveira, @abhinand05 and @piantic! And thanks for sharing your notebooks!", "votes": null }, { "id": "1288435", "postDate": "04/30/2021 02:22:24", "content": "Congratulations!
", "rawMarkdown": "Congratulations!", "votes": null } ], "comments": [ { "id": 1253798, "author_name": "ambarish", "author_url": "", "post_date": "03/27/2021 03:36:19", "content": "Congratulations to the wonderful contributors. This is very nice! I hope to learn a lot from these kernels.
", "votes": null, "replies": [] }, { "id": 1254253, "author_name": "dimitreoliveira", "author_url": "", "post_date": "03/27/2021 13:26:43", "content": "I would like to thanks the Kaggle team and the community for receiving so well my work here, this competition was special for me, I got to make a lot of experiments and publish some of them here with the community. Congratulations to @abhinand05 and @piantic for winning as well.
\nFor anyone else that wants to look in some of the other experiments checkout the GitHub repository, I created for this competition.
", "votes": null, "replies": [ { "id": 1255211, "author_name": "rapela", "author_url": "", "post_date": "03/28/2021 15:14:11", "content": "Excellent job @dimitreoliveira! I think that this kind of work will help a lot the community, and for sure, I will take a look more deeply into your works to inspire and try to do some stuff with TPUs. Muito bom meu velho! 😄🔥💥
", "votes": null, "replies": [] }, { "id": 1255414, "author_name": "dimitreoliveira", "author_url": "", "post_date": "03/28/2021 19:19:32", "content": "Thanks @rapela , I also think that this work is great for the community, um abraco!
", "votes": null, "replies": [] } ] }, { "id": 1254302, "author_name": "piantic", "author_url": "", "post_date": "03/27/2021 14:07:20", "content": "I would like to thank the organizer and the Kaggle team for their efforts to ensure the successful competition. Also thanks to the other kagglers who enjoyed my notebooks and discussions I shared during the competition.
\nI will continue to share good notebooks and discussions in the community. I hope to see all in other competitions.
\np.s. Congratulation on TPU Star award as wall @dimitreoliveira, @abhinand05.
Thank you!
", "votes": null, "replies": [] }, { "id": 1254332, "author_name": "abhinand05", "author_url": "", "post_date": "03/27/2021 14:43:24", "content": "Many thanks to Kaggle Team for awarding my work. Looking forward to contributing more to the community. Happy Kaggling! Congrats to @dimitreoliveira and @piantic as well!
", "votes": null, "replies": [] }, { "id": 1254703, "author_name": "yosukeyama", "author_url": "", "post_date": "03/28/2021 01:51:42", "content": "Congratulations!
\nI believe that all of you deserve the awards. Before I started the cassava competition, I knew only the basics about image classification, but I have learned a lot from your valuable kernels. What I learned from the notebooks was even greater than the competition medal. Thank you very much!
Congratulations TPU stars! @dimitreoliveira @abhinand05 @piantic Thanks for sharing!
", "votes": null, "replies": [] }, { "id": 1261282, "author_name": "saukha", "author_url": "", "post_date": "04/02/2021 22:03:16", "content": "Congratulations, @dimitreoliveira, @abhinand05 and @piantic! And thanks for sharing your notebooks!
", "votes": null, "replies": [] }, { "id": 1288435, "author_name": "jasonkim2984", "author_url": "", "post_date": "04/30/2021 02:22:24", "content": "Congratulations!
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1253505": "Please join me in congratulating our [TPU Stars](https://www.kaggle.com/tpu-stars), awarded to the [most knowledgeable and helpful TPU experts](https://www.kaggle.com/c/cassava-leaf-disease-classification/overview/prizes) in this competition.\n\n✨ [Dimitre Oliveira](https://www.kaggle.com/dimitreoliveira) is now a multiple-time TPU Star award winner. He made tremendous contributions with his TPU expertise to this competition across discussions, dataset (TFRecords) creation, generating data with GANs, & training + inference using multiple approaches. These high quality and easy-to-follow instructive notebooks provide a critical starting point for many to learn with TPUs. Check out his notebooks:\n- [Creating Stratified TFRecords 256x256](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-stratified-tfrecords-256x256)\n- [Tensorflow TPU Training](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-tpu-tensorflow-training) + [Inference](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-tpu-tensorflow-inference)\n- [Supervised Contrastive Learning Overview/Training](https://www.kaggle.com/dimitreoliveira/cassava-leaf-supervised-contrastive-learning) + [Inference](https://www.kaggle.com/dimitreoliveira/cassava-supervised-contrastive-learning-inference)\n- [CycleGAN Data Augmentation](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-cyclegan-data-augmentation)\n- [Training with TPU v2 Pods](https://www.kaggle.com/dimitreoliveira/cassava-leaf-disease-training-with-tpu-v2-pods)\n\n✨ [Abhinand](https://www.kaggle.com/abhinand05) created the widely-popular [Vision Transformer(ViT): Tutorial + Baseline](https://www.kaggle.com/abhinand05/vision-transformer-vit-tutorial-baseline), this competition's most upvoted TPU notebook. It provided an informative and welcoming introduction to vision transformers and a helpful baseline model.\n✨ [Heroseo](https://www.kaggle.com/piantic) authored [[CNN or Transformer]Pytorch XLA(TPU) for Cassava](https://www.kaggle.com/piantic/cnn-or-transformer-pytorch-xla-tpu-for-cassava), a fantastic Data-efficient Image Transformer (DeIT) starter using PyTorch XLA, which. He also shared a [How-to on Fine-tuning](https://www.kaggle.com/piantic/how-to-finetuning-models-pytorch-xla-tpu) as well as [Learning with Noisy Labels](https://www.kaggle.com/piantic/learning-with-noisy-labels-pytorch-xla-tpu), all tremendous PyTorch XLA on TPU resources. His notebooks provide much-desired PyTorch on TPU expertise and also do a nice job of showing how TPUs & GPUs can work together.\n\nAll of these stars will be receiving the monetary prize with this award. Thank you so much for your valuable contributions to the competition and Kaggle broadly!", "1253798": "Congratulations to the wonderful contributors. This is very nice! I hope to learn a lot from these kernels.", "1254253": "I would like to thanks the Kaggle team and the community for receiving so well my work here, this competition was special for me, I got to make a lot of experiments and publish some of them here with the community. Congratulations to @abhinand05 and @piantic for winning as well.\n\nFor anyone else that wants to look in some of the other experiments checkout the [GitHub](https://github.com/dimitreOliveira/Cassava-Leaf-Disease-Classification) repository, I created for this competition.", "1254302": "I would like to thank the organizer and the Kaggle team for their efforts to ensure the successful competition. Also thanks to the other kagglers who enjoyed my notebooks and discussions I shared during the competition. \n\nI will continue to share good notebooks and discussions in the community. I hope to see all in other competitions. \np.s. Congratulation on TPU Star award as wall @dimitreoliveira, @abhinand05.\n\nThank you!", "1254332": "Many thanks to Kaggle Team for awarding my work. Looking forward to contributing more to the community. Happy Kaggling! Congrats to @dimitreoliveira and @piantic as well!", "1254703": "Congratulations!\nI believe that all of you deserve the awards. Before I started the cassava competition, I knew only the basics about image classification, but I have learned a lot from your valuable kernels. What I learned from the notebooks was even greater than the competition medal. Thank you very much!", "1254743": "Congratulations TPU stars! @dimitreoliveira @abhinand05 @piantic Thanks for sharing!", "1255211": "Excellent job @dimitreoliveira! I think that this kind of work will help a lot the community, and for sure, I will take a look more deeply into your works to inspire and try to do some stuff with TPUs. Muito bom meu velho! 😄🔥💥", "1255414": "Thanks @rapela , I also think that this work is great for the community, um abraco!", "1261282": "Congratulations, @dimitreoliveira, @abhinand05 and @piantic! And thanks for sharing your notebooks!", "1288435": "Congratulations!" }, "source": "meta" }