{ "id": 243628, "title": "数据增广与处理++++++++++++", "url": "/competitions/classify-leaves/discussion/243628", "author_name": "", "post_date": "2021-06-03T11:37:38.726047900Z", "votes": 2, "comment_count": 2, "views": 0, "content": "

原增广：
\n transforms.Resize((60,120)),
\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率
\n transforms.RandomCrop((60, 120)), # 随机剪裁
\n transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度
\n transforms.RandomRotation(10), # 依degrees 随机旋转一定角度
\n transforms.ToTensor(),
\n transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std

\n

得分：0.006+
\n现增广：
\n transforms.Compose([
\n transforms.Resize((224,224)),
\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率
\n # transforms.RandomCrop((60, 120)), # 随机剪裁
\n # transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度
\n # transforms.RandomRotation(10), # 依degrees 随机旋转一定角度
\n transforms.ToTensor(),
\n # transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std

\n

得分：0.8+

\n

感觉不同的增广会对模型产生坏的影响

", "messages": [ { "id": "1334282", "postDate": "06/03/2021 11:37:38", "content": "

原增广：
\n transforms.Resize((60,120)),
\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率
\n transforms.RandomCrop((60, 120)), # 随机剪裁
\n transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度
\n transforms.RandomRotation(10), # 依degrees 随机旋转一定角度
\n transforms.ToTensor(),
\n transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std

\n

得分：0.006+
\n现增广：
\n transforms.Compose([
\n transforms.Resize((224,224)),
\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率
\n # transforms.RandomCrop((60, 120)), # 随机剪裁
\n # transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度
\n # transforms.RandomRotation(10), # 依degrees 随机旋转一定角度
\n transforms.ToTensor(),
\n # transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std

\n

得分：0.8+

\n

感觉不同的增广会对模型产生坏的影响

", "rawMarkdown": "原增广：\n transforms.Resize((60,120)),\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率\n transforms.RandomCrop((60, 120)), # 随机剪裁\n transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度\n transforms.RandomRotation(10), # 依degrees 随机旋转一定角度\n transforms.ToTensor(),\n transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std\n\n得分：0.006+\n现增广：\n transforms.Compose([\n transforms.Resize((224,224)),\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率\n # transforms.RandomCrop((60, 120)), # 随机剪裁\n # transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度\n # transforms.RandomRotation(10), # 依degrees 随机旋转一定角度\n transforms.ToTensor(),\n # transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std\n\n得分：0.8+\n\n感觉不同的增广会对模型产生坏的影响", "votes": null }, { "id": "1335006", "postDate": "06/04/2021 00:37:10", "content": "

肯定呀这个，这也是要调的一部分。

", "rawMarkdown": "肯定呀这个，这也是要调的一部分。", "votes": null }, { "id": "1335013", "postDate": "06/04/2021 00:43:29", "content": "

数据增强albumentations包挺好用的，推荐。

", "rawMarkdown": "数据增强albumentations包挺好用的，推荐。", "votes": null } ], "comments": [ { "id": 1335006, "author_name": "wangtf96", "author_url": "", "post_date": "06/04/2021 00:37:10", "content": "

肯定呀这个，这也是要调的一部分。

", "votes": null, "replies": [] }, { "id": 1335013, "author_name": "wangtf96", "author_url": "", "post_date": "06/04/2021 00:43:29", "content": "

数据增强albumentations包挺好用的，推荐。

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1334282": "原增广：\n transforms.Resize((60,120)),\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率\n transforms.RandomCrop((60, 120)), # 随机剪裁\n transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度\n transforms.RandomRotation(10), # 依degrees 随机旋转一定角度\n transforms.ToTensor(),\n transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std\n\n得分：0.006+\n现增广：\n transforms.Compose([\n transforms.Resize((224,224)),\n transforms.RandomHorizontalFlip(p=0.5), #随机水平翻转 选择一个概率\n # transforms.RandomCrop((60, 120)), # 随机剪裁\n # transforms.ColorJitter(0.3, 0.3, 0.2), # 修改亮度、对比度和饱和度\n # transforms.RandomRotation(10), # 依degrees 随机旋转一定角度\n transforms.ToTensor(),\n # transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n # Normalize(mean, std)按通道进行标准化，即先减均值，再除以标准差std\n\n得分：0.8+\n\n感觉不同的增广会对模型产生坏的影响", "1335006": "肯定呀这个，这也是要调的一部分。", "1335013": "数据增强albumentations包挺好用的，推荐。" }, "source": "meta" }