Model performs differently for model.fit and custom training loop #41957
Labels
comp:keras
Keras related issues
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.10
type:bug
Bug
System information
Custom Training Loop vs Model.fit code
The above mentioned code is the custom training loop of a model.
The above code uses model.fit method for training.
Behaviour and code to replicate the Results
But when I run the same code on the same train dataset and validation dataset with all the same parameters, the validation loss obtained is very different in the two cases.
bash import_weights.sh
python train.py --n_samples 1000 --epochs 100 --b_size 50
for model.fitpython train2.py --n_samples 1000 --epochs 100 --b_size 50
for custom trainingThe text was updated successfully, but these errors were encountered: