DRACOyu

Results 10 comments of DRACOyu

can't use deeplabv3_ver1.tar.gz for training or evaluate or inference

@rishizek hello, I meet the same question，as follows: Key Variable not found in checkpoint [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]] I removed the tf.train.init_checkpoint,this problem still remains, I use...

I have the similar problem in evaluate.py,the error is：ensorflow.python.framework.errors_impl.InvalidArgumentError: Number of ways to split should evenly divide the split dimension, but got split_dim 2 (size = 1) and num_split 3

@chenhust1995 hello, I meet the same question，as follows: Key Variable not found in checkpoint [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]] I removed the tf.train.init_checkpoint,this problem still remains, I use...

I have the similar problem in evaluate.py,the error is：ensorflow.python.framework.errors_impl.InvalidArgumentError: Number of ways to split should evenly divide the split dimension, but got split_dim 2 (size = 1) and num_split 3

@chenhust1995 I used lip dataset that the ground-truth picture has single channel，not this reason, I don't use fitune model, why this question still remain

where is the param "--not-restore-last"

@rishizek hello, I meet the same question，as follows: Key Variable not found in checkpoint [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]] I removed the tf.train.init_checkpoint,this problem still remains, I use...

About the video data

@LeslieZhoa hello, I meet the same question，as follows: Key Variable not found in checkpoint [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]] I removed the tf.train.init_checkpoint,this problem still remains, I use...

About the video data

BN的参数默认是不添加到模型中的，需要在代码里要添加保存均值和方差的部分 ------------------ 原始邮件 ------------------ 发件人: "chenhongyun123"; 发送时间: 2019年8月8日(星期四) 晚上10:35 收件人: "rishizek/tensorflow-deeplab-v3-plus"; 抄送: "1254549726";"Mention"; 主题: Re: [rishizek/tensorflow-deeplab-v3-plus] About the video data (#34) @LeslieZhoa Hello,i try to run your code,because you say...

Training or testing python train\testDAN.py

你好，我没有训练呢，我想运行下测试看下效果，

some question

I am a new user,i can not use google,so i want to remove this module,but this is so many error, What do I need to modify?

some question

can you help me to solve it

感谢您的工作！有一些困惑请教！

hello，stage1，text encoder is fix， def make_optimizer_1stage(cfg, model): params = [] keys = [] for key, value in model.named_parameters(): if "prompt_learner" in key: lr = cfg.SOLVER.STAGE1.BASE_LR weight_decay = cfg.SOLVER.STAGE1.WEIGHT_DECAY params +=...