My diagnostic CNN shows high accuracy on data from one hospital.When tested on scans from a different hospital, performance drops drastically.The disease patterns are the same.Only the scanners and imaging pipelines differ.
Decode Trail Latest Questions
The reconstruction loss is very low on training images.But when I test on new data, outputs look distorted.The model seems confident but wrong.It feels like it memorized the dataset.
My GAN generates faces.But many look distorted or unnatural.Eyes and mouths appear in wrong positions.The training seems stable, but outputs are flawed.
The base model worked well before.After fine-tuning on new data, accuracy drops everywhere.Even old categories are misclassified.The model seems to have forgotten what it knew.
My GAN generates images but they look washed out.Many samples look almost identical.Training loss looks stable.But the visual quality never improves.
The training loss drops steadily during fine-tuning.But the translated sentences are grammatically wrong.BLEU and other quality metrics do not improve.It feels like the model is optimizing the wrong thing.
I am training a deep network for a regression task.The loss drops initially but then stops changing.Even after many epochs it never improves.The model is clearly underperforming.
The model classifies upright images correctly.Rotated versions of the same images fail.The content is the same.Only orientation changed.
My RNN works fine on short sequences.When I give it longer inputs, predictions become random.Loss increases with sequence length.It feels like the model forgets earlier information.
Short sequences work fine.Longer sequences cause GPU crashes.No code changes were made.Only input size increased.