Styjun

Why did the Apple //e make a hideous noise if you inserted the disk upside down?

Copy group of files (Filename*) to backup (Filename*.bak)

Is this house-rule removing the increased effect of cantrips at higher character levels balanced?

Installed software from source, how to say yum not to install it from package?

What verb for taking advantage fits in "I don't want to ________ on the friendship"?

Why would Dementors torture a Death Eater if they are loyal to Voldemort?

How far can gerrymandering go?

What is the meaning of 'shout over' in a sentence exactly?

Rear derailleur got caught in the spokes, what could be a root cause

What happens if a caster is surprised while casting a spell with a long casting time?

How to track mail undetectably?

German idiomatic equivalents of 能骗就骗 (if you can trick, then trick)

Is leaving out prefixes like "rauf", "rüber", "rein" when describing movement considered a big mistake in spoken German?

Does friction always oppose motion?

Can US Supreme Court justices / judges be "rotated" out against their will?

Did the Russian Empire have a claim to Sweden? Was there ever a time where they could have pursued it?

How useful would a hydroelectric power plant be in the post-apocalypse world?

Why was Pan Am Flight 103 flying over Lockerbie?

Checkmate in 1 on a Tangled Board

Early 2000s movie about time travel, protagonist travels back to save girlfriend, then into multiple points in future

Russian equivalents of 能骗就骗 (if you can cheat, then cheat)

Does "boire un jus" tend to mean "coffee" or "juice of fruit"?

Avoiding repetition when using the "snprintf idiom" to write text

Is it OK to throw pebbles and stones in streams, waterfalls, ponds, etc.?

Error while loading weights for keras model

How can I convert a trained Tensorflow model to Keras?How to use a trained keras model to do classification in an android applicationKeras model.load_weights(WEIGHTS) provide inaccurate resultsOptimized Deployment of Keras Models?Keras fails to load model weights when using MXNet backendSaving the best weights and model in KerasKeras train_on_batch behaviourError when loading Keras model trained by tensorflowKeras Weights AveragingKeras: Best model according to ModelCheckpoint-callback produces different loss on training set than best epoch loss displayed while training

0

1

I trained a model with Keras and saved weights in a *.hdf5 file during training using callbacks:

callbacks_list = [tf.keras.callbacks.ModelCheckpoint(filepath_checkpoint, monitor='val_loss', verbose=1, save_best_only=True, mode='min')]

When I tried to reload weights into the model using model.load_weights(filepath_checkpoint) I got the following error:

2019-03-25 16:34:20.291041: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open Yolo/weights-best-tiny-test.hdf5: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?

Couls you help me to solve this issue?
Thank you

python tensorflow keras

share|improve this question

asked Mar 25 at 15:48

aleio1aleio1

4877 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Can you provide a self-containing example that reproduces the issue?
  
  – Matias Valdenegro
  Mar 25 at 19:38
  

  
  
  
  

add a comment | 

0

1

I trained a model with Keras and saved weights in a *.hdf5 file during training using callbacks:

callbacks_list = [tf.keras.callbacks.ModelCheckpoint(filepath_checkpoint, monitor='val_loss', verbose=1, save_best_only=True, mode='min')]

When I tried to reload weights into the model using model.load_weights(filepath_checkpoint) I got the following error:

2019-03-25 16:34:20.291041: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open Yolo/weights-best-tiny-test.hdf5: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?

Couls you help me to solve this issue?
Thank you

python tensorflow keras

share|improve this question

asked Mar 25 at 15:48

aleio1aleio1

4877 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Can you provide a self-containing example that reproduces the issue?
  
  – Matias Valdenegro
  Mar 25 at 19:38
  

  
  
  
  

add a comment | 

I trained a model with Keras and saved weights in a *.hdf5 file during training using callbacks:

callbacks_list = [tf.keras.callbacks.ModelCheckpoint(filepath_checkpoint, monitor='val_loss', verbose=1, save_best_only=True, mode='min')]

When I tried to reload weights into the model using model.load_weights(filepath_checkpoint) I got the following error:

2019-03-25 16:34:20.291041: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open Yolo/weights-best-tiny-test.hdf5: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?

Couls you help me to solve this issue?
Thank you

python tensorflow keras

share|improve this question

asked Mar 25 at 15:48

aleio1aleio1

4877 bronze badges

callbacks_list = [tf.keras.callbacks.ModelCheckpoint(filepath_checkpoint, monitor='val_loss', verbose=1, save_best_only=True, mode='min')]

2019-03-25 16:34:20.291041: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open Yolo/weights-best-tiny-test.hdf5: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?

share|improve this question

asked Mar 25 at 15:48

aleio1aleio1

4877 bronze badges

share|improve this question

asked Mar 25 at 15:48

aleio1aleio1

4877 bronze badges

asked Mar 25 at 15:48

aleio1aleio1

4877 bronze badges

asked Mar 25 at 15:48

aleio1aleio1

4877 bronze badges