search

Windaway / FCRN-Depth-Prediction-Tensorflow

Another FCRN for Depth Prediction implement with Tensorflow and Tensorlayer.
GNU General Public License v2.0
11 stars 4 forks source link

运行您的fcrn_train.py文件有错误 #2

Open Shawnnnnn opened 5 years ago

Shawnnnnn commented 5 years ago

在从fcrn.ckpt加载完模型，开始训练后，会在while not coord.should_stop():后报错，具体错误如下： tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 40960 values, but the requested shape has 20480 [[Node: Reshape_1 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](DecodeRaw_1/_23, Reshape_1/shape)]] [[Node: Cast/_25 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_73_Cast", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]] 感谢百忙之中查看我的问题 期待您的回复！

Windaway commented 5 years ago

抱歉，我后来加了旋转增广的代码部分忘了生成tfrecord用了那个文件了，可能需要修改下分辨率，这块主要是我给师弟写的。

Shawnnnnn commented 5 years ago

@Windaway 具体是哪块的分辨率需要修改？

Windaway commented 5 years ago

懒得看了，我师弟那跑已经没啥问题了。

1811081031 commented 5 years ago

在从fcrn.ckpt加载完模型，开始训练后，会在而不是coord.should_stop（）：后报错，具体错误如下： tensorflow.python.framework.errors_impl.InvalidArgumentError：重塑形状的输入是一个具有40960个值的张量，但请求的形状有20480 [[节点：Reshape_1 =重塑[T = DT_FLOAT，Tshape = DT_INT32，_device =“/ job：localhost / replica：0 / task：0 / device：GPU：0”]（DecodeRaw_1 / _23， Reshape_1 / shape）]] [[Node：Cast / _25 = _Recv client_terminated = false，recv_device =“/ job：localhost / replica：0 / task：0 / device：CPU：0”，send_device =“/ job：localhost /副本：0 /任务：0 /设备：GPU：0“，send_device_incarnation = 1，tensor_name =”edge_73_Cast“，tensor_type = DT_FLOAT，_device =”/ job：localhost / replica：0 / task：0 / device：CPU：0 “ ]] 感谢百忙之中查看我的问题 期待您的回复！

您好，请问您这个错误解决了吗？我也遇到这个错误