search

OliverRensu / RTNet

24 stars 3 forks source link

测试数据是怎么组织的？ #3

Open aojue1109 opened 3 years ago

aojue1109 commented 3 years ago

1.您好，我在测试test.py过程中发现DAVIS_dataset = RTTestDataset(dataset, 2, 384, int(384 * 1.75)),其中的dataset不知道如何组织； 2.查看RTTestDataset参数含义发现dataset为以下形式pathes使用：
for path in pathes: file = sorted(os.listdir(os.path.join(path, "img"))) for i in file: self.img_list.append(os.path.join(path, "img", i)) self.label_list.append(os.path.join(path, "label", i[:-3] + "png")) self.fwflow_list.append(os.path.join(path, "flowimg", "fw" + i[:-3] + "png")) self.bwflow_list.append(os.path.join(path, "flowimg", "bw" + i[:-3] + "png"))

其中的img，label等含义不是很清晰，希望能够得到您的帮助，非常感谢

OliverRensu commented 3 years ago

"img" "label" "flow_img" 是指文件夹 我把图片 标签 光流图分别放到了这三个文件夹下面 fw_指的是forward flow 就是t->t+1 bw就是 t ->t-1

suyukun666 commented 2 years ago

"img" "label" "flow_img" 是指文件夹 我把图片 标签 光流图分别放到了这三个文件夹下面 fw_指的是forward flow 就是t->t+1 bw就是 t ->t-1

您好，这个fw_flow和bw_flow是同一个东西来的吗？比如跑flownet2或者RAFT得到一些光流，怎么把这些flow分成fw和bw呢？

OliverRensu commented 2 years ago

fw bw 表示forward 和backward的光流 对于第i张图 forward光流是第i-1 到i backward是i+1到i

suyukun666 @.***> 于2022年2月25日周五 18:30写道：

"img" "label" "flow_img" 是指文件夹 我把图片 标签 光流图分别放到了这三个文件夹下面 fw_指的是forward flow 就是t->t+1 bw就是 t ->t-1

您好，这个fw_flow和bw_flow是同一个东西来的吗？比如跑flownet2或者RAFT得到一些光流，怎么把这些flow分成fw和bw呢？

— Reply to this email directly, view it on GitHub https://github.com/OliverRensu/RTNet/issues/3#issuecomment-1050732360, or unsubscribe https://github.com/notifications/unsubscribe-auth/ANP7CCBBSSDIYYKZEOC2S23U45K6HANCNFSM5D5N3AZA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you commented.Message ID: @.***>

suyukun666 commented 2 years ago

fw bw 表示forward 和backward的光流 对于第i张图 forward光流是第i-1 到i backward是i+1到i suyukun666 @.> 于2022年2月25日周五 18:30写道： … "img" "label" "flow_img" 是指文件夹 我把图片 标签 光流图分别放到了这三个文件夹下面 fw_指的是forward flow 就是t->t+1 bw就是 t ->t-1 您好，这个fw_flow和bw_flow是同一个东西来的吗？比如跑flownet2或者RAFT得到一些光流，怎么把这些flow分成fw和bw呢？ — Reply to this email directly, view it on GitHub <#3 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ANP7CCBBSSDIYYKZEOC2S23U45K6HANCNFSM5D5N3AZA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.>

感谢您的回复，那我想请为一下对于第一张图片和最后一张的图片的fw_flow, bw_flow怎么处理呢

OliverRensu commented 2 years ago

当时同时使用fw 和bw就是考虑到了这种情况 同时使用至少保证第一张的bw有（fw为全黑 第一张到一张）

在 2022年2月25日星期五，suyukun666 @.***> 写道：

fw bw 表示forward 和backward的光流 对于第i张图 forward光流是第i-1 到i backward是i+1到i suyukun666 @.

> 于2022年2月25日周五 18:30写道： … <#m8734523562972918316> "img" "label" "flow_img" 是指文件夹 我把图片 标签 光流图分别放到了这三个文件夹下面 fw_指的是forward flow 就是t->t+1 bw就是 t ->t-1 您好，这个fw_flow和bw_flow是同一个东西来的吗？比如跑flownet2或者RAFT得到一些光流，怎么把这些flow分成fw和bw呢？ — Reply to this email directly, view it on GitHub <#3 (comment) https://github.com/OliverRensu/RTNet/issues/3#issuecomment-1050732360>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ANP7CCBBSSDIYYKZEOC2S23U45K6HANCNFSM5D5N3AZA https://github.com/notifications/unsubscribe-auth/ANP7CCBBSSDIYYKZEOC2S23U45K6HANCNFSM5D5N3AZA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you commented.Message ID: @.>

感谢您的回复，那我想请为一下对于第一张图片和最后一张的图片的fw_flow, bw_flow怎么处理呢

— Reply to this email directly, view it on GitHub https://github.com/OliverRensu/RTNet/issues/3#issuecomment-1050800560, or unsubscribe https://github.com/notifications/unsubscribe-auth/ANP7CCBHBHVXRBEWG7FVBM3U45WZXANCNFSM5D5N3AZA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you commented.Message ID: @.***>