The shape requested by TripletSemiHardLoss for _inferencetrainfunction1666 with a node of TripletSemiHardLoss/PartitionedCall/Reshape and a size of 32 is (None, 32). The first dimension is set to None to account for variable batch sizes during training. The second dimension is fixed at 32 to represent the size of the embedding space for each input example.
Please start posting anonymously - your entry will be published after you log in or create a new account. This space is reserved only for answers. If you would like to engage in a discussion, please instead post a comment under the question or an answer that you would like to discuss
Asked: 2023-06-07 21:48:57 +0000
Seen: 7 times
Last updated: Jun 07 '23
What does the error "Bar 0; array size is too large, maximum size is 100000" mean?
How can the text size of the plot be enlarged using ggcuminc?
How can I transfer the dimensions of a ChartArea from one PowerPoint chart to another?
The size of the plot returned by df.hist() is not the desired one.
How can I sort products that have the size attribute available in stock in Woocommerce?
What is the appropriate size for App store screenshots on a 6.5" display?
How to provide Arduino input parameters of any size without creating a struct?