def main():
"""
Executing relevant functions
"""
# Get Keyword Args for Prediction
args = arg_parser()
# Pre load categories to names json file
if type(args.category_names) == type(None):
category_names = 'cat_to_name.json'
with open(category_names, 'r') as f:
cat_to_name = json.load(f)
# Check for GPU
device = check_gpu(gpu=args.GPU)
# Load model trained with train.py
model = load_checkpoint(args.checkpoint, device, GPU=args.GPU)
# Process Image
image_tensor = process_image(args.image)
# Use `processed_image` to predict the top K most likely classes
top_probs, top_index = predict(args.image, model, cat_to_name, args.top_k,
device)
def main():
"""
Executing relevant functions
"""
# Get Keyword Args for Prediction
args = arg_parser()
# Load categories to names json file
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
# Load model trained with train.py
model = load_checkpoint(args.checkpoint)
# Process Image
image_tensor = process_image(args.image)
# Check for GPU
device = check_gpu(gpu_arg=args.gpu);
# Use `processed_image` to predict the top K most likely classes
top_probs, top_labels, top_flowers = predict(image_tensor, model,
device, cat_to_name,
args.top_k)
# Print out probabilities
print_probability(top_flowers, top_probs)
def main():
"""
Executing relevant functions
"""
# Get Keyword Args for Prediction
args = arg_parser()
# Load categories to names json file
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
# Load model trained with train.py
model = load_checkpoint(args.checkpoint)
# Process Image
image_tensor = process_image(args.image)
# Check for GPU
device = check_gpu(gpu_arg=args.gpu)
probs, labels, flowers = predict(image_tensor, model, device, cat_to_name,
args.top_k)
print_prob(flowers, probs)
def main():
args = arg_parser()
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
model = load_checkpoint(args.checkpoint)
image_tensor = process_image(args.image)
device = check_gpu(gpu_arg=args.gpu);
top_probs, top_labels, top_flowers = predict(image_tensor, model, device, cat_to_name, args.top_k)
print_probability(top_probs, top_flowers)
def main():
arg = args()
with open('cat_to_name.json', 'r') as f:
cat_to_name = json.load(f)
model = checkpoint_loading(arg.checkpoint)
image = process_image(arg.image)
device = check_gpu(arg.gpu)
top_p, top_classes, top_flowers = predict(arg.image, model,cat_to_name,arg.top_k, device)
probabilities(top_p, top_flowers)
def main():
args = args_parser()
with open(args.category_names,'r') as f:
cat_to_name = json.load(f)
model = load_model(args.checkpoint)
device = check_gpu(gpu_arg=args.gpu);
image_path = args.image
top_k = args.top_k
top_ps,top_labels,top_flowers = predict(image_path,model,top_k,cat_to_name,device)
print_probability(top_flowers, top_ps)
def main():
args = fn_parser()
# Load the names of the categories from the json file.
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
model = fn_load_checkpoint(args.checkpoint)
image_tensor = fn_process_image(args.image)
device = check_gpu(gpu_arg=args.gpu)
top_probs, top_labels, top_flowers = fn_predict(image_tensor, model,
device, cat_to_name,
args.top_k)
fn_print_probability(top_flowers, top_probs)
def main():
"""
defining the main function
"""
# Creates & retrieves Command Line Arugments
args = arg_parser()
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
model = load_checkpoint(args.checkpoint)
device = check_gpu(gpu_arg=args.gpu)
print("Type of the Device is :{}".format(device))
top_probs, top_labels, top_flowers = predict(args.dir, model, args.topk, cat_to_name, device)
print_probability(top_flowers, top_probs)
def main():
input = arg_parser()
#loading categories to names
with open(input.category_names, 'r') as f:
cat_to_name = json.load(f)
print('checking for gpu')
device = check_gpu(gpu_arg=input.gpu)
model = load_checkpoint(input.checkpoint)
image_tensor = process_image(input.image_path)
probs_top_list, classes_top_list = predict(input.image_path, model, input.topk)
print(probs, classes)
return probs, classes
def main():
"""
Executing relevant functions
"""
# Get Keyword Args for Prediction
args = arg_parser()
# Load categories to names json file
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
# Load model trained with train.py
model = load_checkpoint(args.checkpoint)
# Process Image
image_tensor = process_image(args.image)
print(image_tensor.shape)
# Check for GPU
device = check_gpu(gpu_arg=args.gpu)
# Carry out prediction
probs, classes = predict(image_tensor, model, args.top_k, device)
# Print out probabilities
# Print probabilities and predicted classes
print(probs)
print(classes)
names = []
for i in classes:
names += [cat_to_name[i]]
print(
f"This flower is most likely to be a: '{names[0]}' with a probability of {round(probs[0]*100,4)}% "
)
Converts two lists into a dictionary to print on screen
"""
for i, j in enumerate(zip(flowers, probs)):
print("Rank {}:".format(i + 1),
"Flower: {}, liklihood: {}%".format(j[1], ceil(j[0] * 100)))
if __name__ == '__main__':
# Get Keyword Args for Prediction
args = arg_parser()
# Load categories to names json file
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
# Load model trained with train.py
model = load_checkpoint(args.checkpoint)
# Process Image
image_tensor = process_image(args.image)
# Check for GPU
device = check_gpu(gpu_arg=args.gpu)
# Use `processed_image` to predict the top K most likely classes
top_probs, top_labels, top_flowers = predict_data(image_tensor, model,
device, cat_to_name,
args.top_k)
# Print out probabilities
probability(top_flowers, top_probs)
