haimeh commented on issue #6629: Not enough information to get shape
URL: 
https://github.com/apache/incubator-mxnet/issues/6629#issuecomment-321357117
 
 
   @thirdwing @nnguyen24 
    
   If you replace the train.x and train.y array with:
   ```
   # Generate testing data
   train.x = matrix(data = rexp(200, rate = 10), nrow = 120, ncol = 6380)
   train.y = matrix(data = rexp(6380, rate = 10), nrow = 120, ncol = 319)
   
   # Reshape testing data
   train.array <- train.x
   dim(train.array) <- c(319,20,120)
   dim(train.y) <- c(319,120)
   
   ```
   You can trigger the error.
   The test set is not necessary to recreate the error.
   
   I experienced the same error with my own fancy loss function.
   I got around it, in the end, by implementing the loss inside a modified 
mx.model.train function (right before backward pass) replacing the symbols with 
mx.nd operations.
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


With regards,
Apache Git Services

Reply via email to