def main():
# Take in camera options
args = sys.argv[1:]
num_args = len(args)
if num_args != 5:
print("Did not input enough camera options")
sys.exit()
iso, cont, brt, sat, shutter = args
#Set Raspistill image options
dir = "/home/pi/"
fileName = "img_" + datetime.now().strftime("%Y-%m-%d_%H-%M-%S") + ".jpg"
cmd = "raspistill --ISO {} --contrast {} -- brightness {} --drc high -k --saturation {} --shutter {} -o ".format(
iso, cont, brt, sat, shutter) + dir + fileName
subprocess.call(cmd, shell=True)
#Print model data
model_wrapper = model.ModelWrapper()
input_shape = model_wrapper.GetInputShape()
output_shape = model_wrapper.GetOutputShape()
preprocessing_metadata = helpers.get_image_preprocessing_metadata(
model_wrapper)
#Open image and run recognition
my_file = Path(fileName)
if not my_file.is_file():
print("File Not Found")
sys.exit()
sample_image = cv2.imread(fileName)
input_data = helpers.prepare_image_for_model(
sample_image,
input_shape.columns,
input_shape.rows,
preprocessing_metadata=preprocessing_metadata)
input_data = model.FloatVector(input_data)
predictions = model_wrapper.Predict(input_data)
prediction_index = int(np.argmax(predictions))
c_file = open("categories.txt", "r")
list_of_categories = [(line.strip()).split() for line in c_file]
c_file.close()
#Print Results
print("Model input shape: [{0.rows}, {0.columns}, {0.channels}]".format(
input_shape))
print("Model output shape: [{0.rows}, {0.columns}, {0.channels}]".format(
output_shape))
print("Category index: {}".format(prediction_index))
print("Confidence: {}".format(predictions[prediction_index]))
print("This object ({}) is a {} with confidence of {}".format(
fileName, list_of_categories[prediction_index],
predictions[prediction_index]))
def main():
camera = cv2.VideoCapture(0)
# request a specific resolution (sometimes the camera has very small default resolution)
helpers.set_camera_resolution(camera, 1280, 720)
with open("categories.txt", "r") as categories_file:
categories = categories_file.read().splitlines()
# Get the model wrapper in order to interact with the model
model_wrapper = model.ModelWrapper()
input_shape = model_wrapper.GetInputShape()
output_shape = model_wrapper.GetOutputShape()
# Get the model-specific preprocessing metadata
preprocessing_metadata = helpers.get_image_preprocessing_metadata(model_wrapper)
while (cv2.waitKey(1) & 0xFF) != 27:
# Get the image from the camera
original = get_image_from_camera(camera)
# Prepare the image to pass to the model. This helper crops and resizes
# the image maintaining proper aspect ratio and return the resultant
# image instead of a numpy array. Additionally, the helper will
# reorder the image from BGR to RGB
image, offset, scale = helpers.prepare_image_for_model(
original, input_shape.columns, input_shape.rows, reorder_to_rgb=True,
ravel=False, preprocessing_metadata=preprocessing_metadata)
# Wrap the resulting numpy array in a FloatVector
input_data = model.FloatVector(image)
# Get the predictions by running the model. `predictions` is returned
# as a flat array
predictions = model_wrapper.Predict(input_data)
# Reshape the output of the model into a tensor that matches the
# expected shape
predictions = np.reshape(
predictions,
(13, 13, 125))
# Do some post-processing to extract the regions from the output of
# the model
regions = helpers.get_regions(
predictions, categories, CONFIDENCE_THRESHOLD, ANCHOR_BOXES)
# Get rid of any overlapping regions for the same object
regions = helpers.non_max_suppression(
regions, OVERLAP_THRESHOLD, categories)
# Draw the regions onto the image
scale = (scale[0] * image.shape[1], scale[1] * image.shape[0])
helpers.draw_regions_on_image(original, regions, offset, scale)
# Display the image
cv2.imshow("Region detection", original)
def process_frame(frame, categories, frame_count, output_frame_path):
if frame is None:
print("Not valid input frame! Skip...")
return
# Get the model's input shape. We will use this information later to resize
# images appropriately.
input_shape = model.get_default_input_shape()
# Get the model's output shape and create an array to hold the model's
# output predictions
output_shape = model.get_default_output_shape()
predictions = model.FloatVector(output_shape.Size())
# Prepare an image for processing
# - Resize and center-crop to the required width and height while
# preserving aspect ratio.
# - OpenCV gives the image in BGR order. If needed, re-order the
# channels to RGB.
# - Convert the OpenCV result to a std::vector<float>
input_data = helpers.prepare_image_for_model(
frame, input_shape.columns, input_shape.rows)
# Send the image to the compiled model and fill the predictions vector
# with scores, measure how long it takes
start = time.time()
model.predict(input_data, predictions)
end = time.time()
# Get the value of the top 5 predictions
top_5 = helpers.get_top_n(predictions, 5)
if (len(top_5) > 0):
# Generate header text that represents the top5 predictions
header_text = ", ".join(["({:.0%}) {}".format(
element[1], categories[element[0]]) for element in top_5])
helpers.draw_header(frame, header_text)
# Generate footer text that represents the mean evaluation time
time_delta = end - start
footer_text = "{:.0f}ms/frame".format(time_delta * 1000)
helpers.draw_footer(frame, footer_text)
# save the processed frame
output_file_path = os.path.join(output_frame_path, "recognized_{}.png".format(frame_count))
cv2.imwrite(output_file_path, frame)
print("Processed frame {}: header text: {}, footer text: {}".format(frame_count, header_text, footer_text))
return header_text
else:
print("Processed frame {}: No recognized frame!")
return None
def input_callback(self):
"""The input callback that returns an image to the model"""
# Get an image from the camera. If you'd like to use a different image,
# load the image from some other source.
self.image = get_image_from_camera(self.camera)
# Prepare the image to pass to the model. This helper:
# - crops and resizes the image maintaining proper aspect ratio
# - reorders the image channels if needed
# - returns the data as a ravelled numpy array of floats so it can be
# handed to the model
return model.FloatVector(helpers.prepare_image_for_model(
self.image, self.input_shape.columns, self.input_shape.rows, preprocessing_metadata=self.preprocessing_metadata))
def main():
init_GPIO()
init_camera()
init_options()
shoot_categories = set([504])
with open("categories.txt", "r") as categories_file:
categories = categories_file.read().splitlines()
model_wrapper = model.ModelWrapper()
input_shape = model_wrapper.GetInputShape()
preprocessing_metadata = helpers.get_image_preprocessing_metadata(
model_wrapper)
while (cv2.waitKey(1) & 0xFF) == 0xFF:
image = get_image_from_camera(camera)
input_data = helpers.prepare_image_for_model(
image,
input_shape.columns,
input_shape.rows,
preprocessing_metadata=preprocessing_metadata)
input_data = model.FloatVector(input_data)
predictions = model_wrapper.Predict(input_data)
top_5 = helpers.get_top_n(predictions, 5)
header_text = ", ".join([
"({:.0%}) {}".format(element[1], categories[element[0]])
for element in top_5
])
helpers.draw_header(image, header_text)
if top_5:
print(header_text)
release_shutter()
for element in top_5:
if verbose:
print(element[0])
if element[0] in shoot_categories:
press_shutter()
break
cv2.imshow("BirdWatcher", image)
rawCapture.truncate(0)
def main():
camera = cv2.VideoCapture(0)
with open("categories.txt", "r") as categories_file:
categories = categories_file.read().splitlines()
model_wrapper = model.ModelWrapper()
input_shape = model_wrapper.GetInputShape()
preprocessing_metadata = helpers.get_image_preprocessing_metadata(
model_wrapper)
while (cv2.waitKey(1) & 0xFF) == 0xFF:
image = get_image_from_camera(camera)
input_data = helpers.prepare_image_for_model(
image,
input_shape.columns,
input_shape.rows,
preprocessing_metadata=preprocessing_metadata)
input_data = model.FloatVector(input_data)
predictions = model_wrapper.Predict(input_data)
top_5 = helpers.get_top_n(predictions, 5)
header_text = ", ".join([
"({:.0%}) {}".format(element[1], categories[element[0]])
for element in top_5
])
helpers.draw_header(image, header_text)
cv2.imshow("ELL model", image)
def main():
"""Entry point for the script when called directly"""
# Open the video camera. To use a different camera, change the camera
# index.
camera = cv2.VideoCapture(0)
# Read the category names
with open("dogs.txt", "r") as dogs_file,\
open("cats.txt", "r") as cats_file:
dogs = dogs_file.read().splitlines()
cats = cats_file.read().splitlines()
# Get the model wrapper in order to interact with the model
model_wrapper = model.ModelWrapper()
# Get the model's input dimensions. We'll use this information later to
# resize images appropriately.
input_shape = model_wrapper.GetInputShape()
# Get the model-specific preprocessing metadata
preprocessing_metadata = helpers.get_image_preprocessing_metadata(
model_wrapper)
while (cv2.waitKey(1) & 0xFF) == 0xFF:
# Get an image from the camera. If you'd like to use a different image,
# load the image from some other source.
image = get_image_from_camera(camera)
# Prepare the image to pass to the model. This helper:
# - crops and resizes the image maintaining proper aspect ratio
# - reorders the image channels if needed
# - returns the data as a ravelled numpy array of floats so it can be
# handed to the model
input_data = helpers.prepare_image_for_model(
image,
input_shape.columns,
input_shape.rows,
preprocessing_metadata=preprocessing_metadata)
# Wrap the resulting numpy array in a FloatVector
input_data = model.FloatVector(input_data)
# Get the predicted classes using the model's predict function on the
# image input data. The predictions are returned as a numpy array with the
# probability that the image # contains the class represented by that
# index.
predictions = model_wrapper.Predict(input_data)
# Let's grab the value of the top prediction and its index, which
# represents the top most confident match and the class or category it
# belongs to.
top_n = helpers.get_top_n(predictions, 1, threshold=0.05)
# See whether the prediction is in one of our groups
group = ""
label = ""
if top_n:
top = top_n[0][0]
if prediction_index_in_set(top, dogs):
group = "Dog"
elif prediction_index_in_set(top, cats):
group = "Cat"
header_text = ""
if group:
# A group was detected, so take action
top = top_n[0]
take_action(group)
header_text = "({:.0%}) {}".format(top[1], group)
helpers.draw_header(image, header_text)
# Display the image using opencv
cv2.imshow("Grouping", image)
# Return as a vector of floats
result = resized.astype(np.float).ravel()
return result
# Get the input and output shapes
input_shape = model.get_default_input_shape()
output_shape = model.get_default_output_shape()
print("Model input shape: " +
str([input_shape.rows, input_shape.columns, input_shape.channels]))
print("Model output shape: " +
str([output_shape.rows, output_shape.columns, output_shape.channels]))
# Create a blank output of the appropriate size to hold the prediction results
predictions = model.FloatVector(output_shape.Size())
# Read in the sample image
image = cv2.imread("coffeemug.jpg")
# Prepare the image to send to the model
input = prepare_image_for_model(image, input_shape.columns, input_shape.rows)
# Send the input to the predict function and get the prediction result
model.predict(input, predictions)
# Print the index of the highest confidence prediction
predictionIndex = int(np.argmax(predictions))
print("Category index: " + str(predictionIndex))
print("Confidence: " + str(predictions[predictionIndex]))
# Get the model-specific preprocessing metadata
preprocessing_metadata = helpers.get_image_preprocessing_metadata(
model_wrapper)
print("Model input shape: [{0.rows}, {0.columns}, {0.channels}]".format(
input_shape))
print("Model output shape: [{0.rows}, {0.columns}, {0.channels}]".format(
output_shape))
# Read in the sample image
sample_image = cv2.imread("coffeemug.jpg")
# Prepare the image to send to the model
input_data = helpers.prepare_image_for_model(
sample_image,
input_shape.columns,
input_shape.rows,
preprocessing_metadata=preprocessing_metadata)
# Wrap the resulting numpy array in a FloatVector
input_data = model.FloatVector(input_data)
# Send the input to the predict function and get the prediction result
predictions = model.predict(input_data)
# Print the index of the highest confidence prediction
prediction_index = int(np.argmax(predictions))
print("Category index: {}".format(prediction_index))
print("Confidence: {}".format(predictions[prediction_index]))
def main():
# Open the video camera. To use a different camera, change the camera index.
camera = cv2.VideoCapture(0)
# Read the category names
categories = open('categories.txt', 'r').read().splitlines()
dogs = open('dogs.txt', 'r').read().splitlines()
cats = open('cats.txt', 'r').read().splitlines()
# Get the model's input dimensions. We'll use this information later to resize images appropriately.
inputShape = model.get_default_input_shape()
# Create a vector to hold the model's output predictions
outputShape = model.get_default_output_shape()
predictions = model.FloatVector(outputShape.Size())
headerText = ""
while ((cv2.waitKey(1) & 0xFF) == 0xFF):
# Get an image from the camera. If you'd like to use a different image, load the image from some other source.
image = get_image_from_camera(camera)
# Prepare the image to pass to the model. This helper:
# - crops and resizes the image maintaining proper aspect ratio
# - reorders the image channels if needed
# - returns the data as a ravelled numpy array of floats so it can be handed to the model
input = helpers.prepare_image_for_model(image, inputShape.columns,
inputShape.rows)
# Get the predicted classes using the model's predict function on the image input data.
# The predictions are returned as a vector with the probability that the image
# contains the class represented by that index.
model.predict(input, predictions)
# Let's grab the value of the top prediction and its index, which represents the top most
# confident match and the class or category it belongs to.
topN = helpers.get_top_n(predictions, 1, threshold=0.05)
# See whether the prediction is in one of our groups
group = ""
caption = ""
label = ""
if len(topN) > 0:
top = topN[0]
label = categories[top[0]]
if label_in_set(label, dogs):
group = "Dog"
elif label_in_set(label, cats):
group = "Cat"
if not group == "":
# A group was detected, so take action
top = topN[0]
take_action(group)
headerText = "(" + str(int(top[1] * 100)) + "%) " + group
else:
# No group was detected
headerText = ""
helpers.draw_header(image, headerText)
# Display the image using opencv
cv2.imshow('Grouping', image)
def main():
# Open the video camera. To use a different camera, change the camera
# index.
camera = cv2.VideoCapture(0)
# Read the category names
with open("categories.txt", "r") as categories_file:
categories = categories_file.read().splitlines()
# Get the model's input shape. We will use this information later to resize
# images appropriately.
input_shape = model.get_default_input_shape()
# Get the model's output shape and create an array to hold the model's
# output predictions
output_shape = model.get_default_output_shape()
predictions = model.FloatVector(output_shape.Size())
# Declare a variable to hold the prediction times
prediction_times = []
mean_time_to_predict = 0.0
while (cv2.waitKey(1) & 0xFF) == 0xFF:
# Get an image from the camera.
image = get_image_from_camera(camera)
# Prepare an image for processing
# - Resize and center-crop to the required width and height while
# preserving aspect ratio.
# - OpenCV gives the image in BGR order. If needed, re-order the
# channels to RGB.
# - Convert the OpenCV result to a std::vector<float>
input_data = helpers.prepare_image_for_model(image,
input_shape.columns,
input_shape.rows)
# Send the image to the compiled model and fill the predictions vector
# with scores, measure how long it takes
start = time.time()
model.predict(input_data, predictions)
end = time.time()
# Get the value of the top 5 predictions
top_5 = helpers.get_top_n(predictions, 5)
# Generate header text that represents the top5 predictions
header_text = ", ".join([
"({:.0%}) {}".format(element[1], categories[element[0]])
for element in top_5
])
helpers.draw_header(image, header_text)
# Generate footer text that represents the mean evaluation time
mean_time_to_predict = helpers.get_mean_duration(
prediction_times, end - start)
footer_text = "{:.0f}ms/frame".format(mean_time_to_predict * 1000)
helpers.draw_footer(image, footer_text)
# Display the image
cv2.imshow("ELL model", image)
print("Mean prediction time: {:.0f}ms/frame".format(mean_time_to_predict *
1000))