@article{
 title = {A guide to convolution arithmetic for deep learning},
 type = {article},
 year = {2018},
 keywords = {Computer Science - Machine Learning,Computer Science - Neural and Evolutionary Comput,Statistics - Machine Learning},
 websites = {http://arxiv.org/abs/1603.07285},
 month = {1},
 id = {022df87d-5f6d-3839-8e10-73cbe008648a},
 created = {2022-03-28T09:45:03.618Z},
 accessed = {2022-03-26},
 file_attached = {true},
 profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
 group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
 last_modified = {2022-03-29T08:05:36.063Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {dumoulinGuideConvolutionArithmetic2018},
 source_type = {article},
 notes = {arXiv: 1603.07285},
 private_publication = {false},
 abstract = {We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers, as well as the relationship between convolutional and transposed convolutional layers. Relationships are derived for various cases, and are illustrated in order to make them intuitive.},
 bibtype = {article},
 author = {Dumoulin, Vincent and Visin, Francesco},
 journal = {arXiv:1603.07285 [cs, stat]}
}

{"_id":"NpzP8ckefvMzk6Kd9","bibbaseid":"dumoulin-visin-aguidetoconvolutionarithmeticfordeeplearning-2018","author_short":["Dumoulin, V.","Visin, F."],"bibdata":{"title":"A guide to convolution arithmetic for deep learning","type":"article","year":"2018","keywords":"Computer Science - Machine Learning,Computer Science - Neural and Evolutionary Comput,Statistics - Machine Learning","websites":"http://arxiv.org/abs/1603.07285","month":"1","id":"022df87d-5f6d-3839-8e10-73cbe008648a","created":"2022-03-28T09:45:03.618Z","accessed":"2022-03-26","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-03-29T08:05:36.063Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"dumoulinGuideConvolutionArithmetic2018","source_type":"article","notes":"arXiv: 1603.07285","private_publication":false,"abstract":"We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers, as well as the relationship between convolutional and transposed convolutional layers. Relationships are derived for various cases, and are illustrated in order to make them intuitive.","bibtype":"article","author":"Dumoulin, Vincent and Visin, Francesco","journal":"arXiv:1603.07285 [cs, stat]","bibtex":"@article{\n title = {A guide to convolution arithmetic for deep learning},\n type = {article},\n year = {2018},\n keywords = {Computer Science - Machine Learning,Computer Science - Neural and Evolutionary Comput,Statistics - Machine Learning},\n websites = {http://arxiv.org/abs/1603.07285},\n month = {1},\n id = {022df87d-5f6d-3839-8e10-73cbe008648a},\n created = {2022-03-28T09:45:03.618Z},\n accessed = {2022-03-26},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-03-29T08:05:36.063Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {dumoulinGuideConvolutionArithmetic2018},\n source_type = {article},\n notes = {arXiv: 1603.07285},\n private_publication = {false},\n abstract = {We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers, as well as the relationship between convolutional and transposed convolutional layers. Relationships are derived for various cases, and are illustrated in order to make them intuitive.},\n bibtype = {article},\n author = {Dumoulin, Vincent and Visin, Francesco},\n journal = {arXiv:1603.07285 [cs, stat]}\n}","author_short":["Dumoulin, V.","Visin, F."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/15ebd17f-e442-d075-0976-73645a7a0b8e/Dumoulin_and_Visin___2018___A_guide_to_convolution_arithmetic_for_deep_learnin.pdf.pdf","Website":"http://arxiv.org/abs/1603.07285"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"dumoulin-visin-aguidetoconvolutionarithmeticfordeeplearning-2018","role":"author","keyword":["Computer Science - Machine Learning","Computer Science - Neural and Evolutionary Comput","Statistics - Machine Learning"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["nZHrFJKyxKKDaWYM8","2252seNhipfTmjEBQ","f9QNc6eirHM3cmhSh","qAPjQpsx8e9aJNrSa"],"keywords":["computer science - machine learning","computer science - neural and evolutionary comput","statistics - machine learning"],"search_terms":["guide","convolution","arithmetic","deep","learning","dumoulin","visin"],"title":"A guide to convolution arithmetic for deep learning","year":2018}