CODEWITHSUNDEEP
tensorflowmachine-learningdeep-learningkerasimagenet
Rehan Aziz
Rehan Aziz

Reputation: 123

how to write predict_generator output to a file over a loop?

i have a large dataset of images on which i want to run the predict_generator. i cannot run on all of them at once due to memory issues. the idea is to

feeding small set of images iteratively to generator by looping over the range of images and making predictions for it.

saving the predictions to a file

later opening the file in a loop to read all the prediction for calculating the probabilites as mentioned in the code.

validation_generator = ImageDataGenerator(rescale=1./255).flow_from_directory(path, target_size=(img_width, img_height),
                                                        batch_size=6,shuffle=False)


print("generator built")
print (counter)
#file = open('Failed.py', 'w')
#for x in file:
 #   for i in range(counter):
  #      features = model.predict_generator(validation_generator,steps=2)



print("features found")

model = Sequential()
model.add(Flatten(input_shape=(3, 3, 1536)))
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(6, activation='softmax'))
model.load_weights(top_model_weights_path)
print("top model loaded")
prediction_proba = model.predict_proba(features)
prediction_classes = model.predict_classes(features)
print(prediction_proba)
print(prediction_classes)
print("original file names")
print(validation_generator.filenames)

the question is that how should the different prediction be saved in one single file. i have tried creating a for loop for file but not sure how it should work? it would be nice if some one could give hints for the goals defined.

Upvotes: 0

Views: 1310

Answers (1)

Daniel Möller
Daniel Möller

Reputation: 86600

Predicting and saving

i = 0
maximumPredictions = ??
for x,y in generator: #if the generator doesn't have y, use only "for x in..."
    predictions = model.predict(x)
    numpy.save('predictions/prediction' + str(i) +".npy", predictions)
    i+=1

    if i == maximumPredictions:
        break;

Loading and processing

files = [name for name in os.listdir('predictions')]
for file in files:
    prediction = numpy.load('predictions/"+file)

    #do what you want with the loaded predictions.

Upvotes: 2

Related Questions