Sardor Muminov
Sardor Muminov
@vividvilla you check it with your online [demo](https://cdn.rawgit.com/vividvilla/csvtotable/master/sample/goog.html). Just click on `Date` table column.
The same error occurs on my side too. My initial dataset was in RGB and converted it using ImageMagick to greyscale PNG file.
@tobimichigan I am not maintainer of this repo. I am also issue-reporter like you. Let's wait what @sdsubhajitdas thinks about this.
@LJ-20 can you share your experience? I cannot run custom unet with multi-gpu. I followed distributed training part in Tensorflow documentation, but no luck. It seems I need to refactor...
@karolzak I haven't tried `tf.keras.utils.multi_gpu_model` since it is deprecated. But, I tried with `tf.distribute.MirroredStrategy()`. And, here is my code: ```python from keras_unet.models import custom_unet from keras.callbacks import ModelCheckpoint from keras.optimizers...
@karolzak fyi, using `multi_gpu_model` raises following exception: ``` ValueError: ('Expected `model` argument to be a `Model` instance, got ', ) ``` Edit: format
@karolzak > @muminoff, can you specify the version that you're using for TF/Keras? This seem to be related to that problem. ``` tf.__version__ '2.1.0' keras.__version__ '2.3.1' ``` > Hmm.. looking...
@karolzak I tried different methods as you described, left only building and compiling the model inside the strategy context, same error. The aboveshown snippet is the latest try. You can...