def main():
"""
Script to export results for Kaggle, Images are read one by one
"""
args = doParsing()
print(args)
# Load model with custom object for mobilenet
model = load_model(args.modelPath,
custom_objects={
'relu6': mobilenet.relu6,
'DepthwiseConv2D': mobilenet.DepthwiseConv2D
})
print("Loaded model from " + args.modelPath)
print(model.summary())
# Dogs and cats test dataset has 12500 samples
results = []
for file in sorted(glob.glob(args.datasetTestDir + "/*.jpg")):
# One by one image prediction
# Image processing (resize and inception like preprocessing to have [-1.0, 1.0] input range)
image = imread(file)
image = imresize(image, size=model.input_shape[1:3])
image = image.astype(np.float32)
processedImage = mobilenet.preprocess_input(image)
# Add 1st dimension for image index in batch
processedImage = np.expand_dims(processedImage, axis=0)
# Get and print TOP1 class
result = model.predict_classes(x=processedImage,
batch_size=1,
verbose=False)
print(os.path.basename(file) + " -> " + classes[result[0]])
# Get and save dog probability
resultProba = model.predict_proba(x=processedImage,
batch_size=1,
verbose=False)
results.append(
(os.path.basename(file)[:os.path.basename(file).rfind('.')],
resultProba[0][classes.index("dog")]))
print("Test finished")
if args.kaggleExportFile is not None:
exportResults(results, args.kaggleExportFile)
def main():
"""
Predictions for images without labels, images are read one by one and you can export results.
It works only with mobilenet.
"""
# TODO: Add a generic load model
args = doParsing()
print(args)
model = load_model(args.modelPath,
custom_objects={
'relu6': mobilenet.relu6,
'DepthwiseConv2D': mobilenet.DepthwiseConv2D
})
print("Loaded model from " + args.modelPath)
print(model.summary())
results = []
for file in tqdm(sorted(glob.glob(args.datasetTestDir + "/*.jpg"))):
# One by one image prediction
# Image processing (resize and inception like preprocessing to have [-1.0, 1.0] input range)
image = imread(file)
image = imresize(image, size=model.input_shape[1:3])
image = image.astype(np.float32)
processedImage = mobilenet.preprocess_input(image)
# Add 1st dimension for image index in batch
processedImage = np.expand_dims(processedImage, axis=0)
# Get and save dog probability
resultProba = model.predict_proba(x=processedImage,
batch_size=1,
verbose=False)
results.append(
(os.path.basename(file)[:os.path.basename(file).rfind('.')],
resultProba[0]))
print("Test finished")
if args.kaggleExportFile is not None:
exportResults(results, args.labelsFile, args.kaggleExportFile)
print("Results for kaggle saved in " + args.kaggleExportFile)
def main():
"""
Script to export results for Kaggle, Images are read one by one
"""
args = doParsing()
print(args)
# Load model
model = tc.load_model(args.modelPath)
print("Loaded model from " + args.modelPath)
# Dogs and cats test dataset has 12500 samples
results = []
# One by one image prediction
for imageFile in sorted(glob.glob(args.datasetTestDir + "/*.jpg")):
# Load image as tc Image, no explicit resize to model input size
image = tc.Image(imageFile)
# Single image SFrame compatible with model utility functions
sframe = tc.SFrame(data={"features": [image]})
# Get and print TOP1
probabilities = model.predict(sframe, output_type="probability_vector")
print(
os.path.basename(imageFile) + " -> " +
model.classes[int(np.argmax(probabilities.to_numpy()[0]))])
# Get and save dog probability
results.append((os.path.basename(
imageFile)[:os.path.basename(imageFile).rfind('.')],
probabilities[0][model.classes.index("dog")]))
print("Test finished")
if args.kaggleExportFile is not None:
exportResults(results, args.kaggleExportFile)
def main():
"""
Example of predict_generator usage for images without labels, images are read one by one and you can export results
"""
# TODO: Add a generic load model
args = doParsing()
print(args)
model = joblib.load(args.modelPath)
print("Loaded model from " + args.modelPath)
results = []
for file in tqdm(sorted(glob.glob(args.datasetTestDirs[0] + "/*.npy"))):
# One by one image prediction
features = []
features.append(np.load(file))
if len(args.datasetTestDirs) > 1:
for datasetTestDir in args.datasetTestDirs[1:]:
features.append(
np.load(
os.path.join(datasetTestDir, os.path.basename(file))))
# Get probabilities
resultProba = model.predict_proba(
np.concatenate(features).reshape(1, -1))
results.append(
(os.path.basename(file)[:os.path.basename(file).rfind('.')],
resultProba[0]))
print("Test finished")
if args.kaggleExportFile is not None:
exportResults(results, args.labelsFile, args.kaggleExportFile)
print("Results for kaggle saved in " + args.kaggleExportFile)
def main():
"""
Script to export results for Kaggle, Images are read one by one
"""
args = doParsing()
print(args)
# Load config (it includes preprocessing type)
config = ConfigParams(args.configFile)
# Load model
model = TensorflowModel(args.modelPath)
print("Loaded model from " + args.modelPath)
# Dogs and cats test dataset has 12500 samples
results = []
inputPlaceholder = model.getGraph().get_tensor_by_name(config.inputName +
":0")
outputTensor = model.getGraph().get_tensor_by_name(config.outputName +
":0")
# One by one image prediction forcing CPU usage
with model.getSession() as sess:
with tf.device("/cpu:0"):
for file in sorted(glob.glob(args.datasetTestDir + "/*.jpg")):
image = ImageUtils.loadImage(file)
# Resize image and preprocess (inception or vgg preprocessing based on config)
processedImage = ImageUtils.preprocessing(
image=image,
width=config.inputSize,
height=config.inputSize,
preprocessingType=config.preprocessType,
meanRGB=config.meanRGB)
# Convert colorspace
processedImage = ImageUtils.convertImageFormat(
processedImage, format=config.inputFormat)
# Add 1st dimension for image index in batch
processedImage = np.expand_dims(processedImage, axis=0)
# Get and print TOP1 class
result = sess.run(outputTensor,
feed_dict={inputPlaceholder: processedImage})
print(
os.path.basename(file) + " -> " +
classes[int(np.argmax(result[0]))])
# Get and save dog probability
results.append((
os.path.basename(file)[:os.path.basename(file).rfind('.')],
result[0][classes.index("dog")]))
print("Test finished")
if args.kaggleExportFile is not None:
exportResults(results, args.kaggleExportFile)