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()
# 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 get the predictions numpy array
# with scores, measure how long it takes
start = time.time()
predictions = model.predict(input_data)
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))
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 output_callback(self, predictions):
"""The output callback that the model calls when predictions are ready"""
header_text = ""
group, probability = self.get_group(predictions)
if group:
# A group was detected, so take action
if group == "Dog":
# A prediction in the dog category group was detected, print a `woof`
print("Woof!")
elif group == "Cat":
# A prediction in the cat category group was detected, print a `meow`
print("Meow!")
header_text = "({:.0%}) {}".format(probability, group)
helpers.draw_header(self.image, header_text)
cv2.imshow("Grouping (with callbacks)", self.image)
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)
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()
# Define the models we'll be using
models = [model1, model2]
# Get the models' input dimensions. We'll use this information later to
# resize images appropriately.
input_shapes = [model.get_default_input_shape() for model in models]
# Create vectors to hold the models' output predictions
prediction_arrays = [
model.FloatVector(model.get_default_output_shape()) for model in models
]
# Declare a value to hold the prediction times
prediction_times = [list(), list()]
mean_time_to_predict = [0.0, 0.0]
# Declare a tiled image used to compose our results
tiled_image = helpers.TiledImage(len(models))
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)
# Run through models in random order to get a fairer average of
# evaluation time
model_indices = np.arange(len(models))
np.random.shuffle(model_indices)
for model_index in model_indices:
model = models[model_index]
# 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_shapes[model_index].columns,
input_shapes[model_index].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.
start = time.time()
model.predict(input_data, prediction_arrays[model_index])
end = time.time()
# Let's grab the value of the top 5 predictions and their index,
# which represents the top five most confident matches and the
# class or category they belong to.
top_5 = helpers.get_top_n(prediction_arrays[model_index],
n=5,
threshold=0.10)
# Draw header text that represents the top five predictions
header_text = "".join([
"({:.0%}) {} ".format(element[1], categories[element[0]])
for element in top_5
])
model_frame = np.copy(image)
helpers.draw_header(model_frame, header_text)
# Draw footer text representing the mean evaluation time
mean_time_to_predict[model_index] = helpers.get_mean_duration(
prediction_times[model_index], end - start)
footer_text = "{:.0f}ms/frame".format(
mean_time_to_predict[model_index] * 1000)
helpers.draw_footer(model_frame, footer_text)
# Set the image with the header and footer text as one of the tiles
tiled_image.set_image_at(model_index, model_frame)
tiled_image.show()