def infer():
""" Given a model handle and input values, this def runs the model inference graph and returns the predictions.
Args: Model handle, input values.
Returns: A JSON containing all the model predictions.
"""
args = {k: v for k, v in request.forms.iteritems()}
print(args)
# clear_session() # Clears TF graphs.
clear_session() # Clears TF graphs.
clear_thread_cache(
) # We need to clear keras models since graph is deleted.
try:
model = get_model(args['handle'])
except Exception as e:
return json.dumps({
'status': 'ERROR',
'why': 'Infer: Model probably not found ' + str(e)
})
if 'values' not in args:
return json.dumps({'status': 'ERROR', 'why': 'No values specified'})
print(args['handle'])
print(args['values'])
outputs = model.infer(json.loads(args['values']))
return json.dumps({'status': 'OK', 'result': outputs})
def train_status():
""" Grabs the metrics from disk and returns them for the given model handle.
Args: Model handle.
Returns: A JSON with a dictionary of keras_model_name -> metric_name -> list(metric values)
"""
args = {k: v for k, v in request.forms.iteritems()}
try:
model = get_model(args['handle'])
except:
return json.dumps({
'status': 'ERROR',
'why': 'Model probably not found'
})
if not model:
return json.dumps({'status': 'ERROR', 'why': 'Concurrency error'})
if model.status == ModelStatus.TRAINED:
return json.dumps({'status': 'DONE'})
losses = {}
for model_name, value_dict in model.val_losses.iteritems():
for metric_name, vals in value_dict.iteritems():
if model_name in losses:
losses[model_name][metric_name] = [
handleNaN(x) for x in vals[-LOSS_LENGTH:]
]
else:
losses[model_name] = {
metric_name: [handleNaN(x) for x in vals[-LOSS_LENGTH:]]
}
return json.dumps({'status': 'OK', 'val_losses': losses})
def infer_types(args, files):
""" Given a model handle, returns a dictionary of column-name to type JSON.
Args: Model handle
Returns: a JSON holding the column-name to type map.
"""
try:
model = get_model(args['handle'])
except Exception as e:
return json.dumps({'status': 'ERROR', 'why': 'Model probably not found ' + str(e)})
return json.dumps({'status': 'OK', 'types': model.types})
def get(self, model_id):
if self.cache.get(model_id, None):
result = get_model(model_id)
if result is None:
return None
if len(self.cache.keys()) == model_cache_size:
#evict the first model
self.cache.pop(self.cache.keys()[0])
self.cache["model_id"] = Model(model_id, result["i"],
result["j"], result["k"])
return self.cache.get(model_id, None)
def train(args, files):
""" Runs the training for the given model.
Args: Model handle.
Returns: A JSON confirming that training has been kicked-off.
"""
clear_session() # Clears TF graphs.
clear_thread_cache() # We need to clear keras models since graph is deleted.
try:
model = get_model(args['handle'])
except:
return json.dumps({'status': 'ERROR', 'why': 'Model probably not found'})
model.start_training()
return json.dumps({'status': 'OK', 'handle': model.get_handle()})