def activate(self):
pred = predict(self.inputs, self.weights)
if self.activation_function:
pred = self.activation_function(pred) + self.bias
self.inputs = [None] * len(self.inputs)
for cb in self.observers:
cb(pred)
def simple_case():
features = [1.0, 3.0, 2.0]
weights = [0, 0, 0]
goal_pred = 10.0
alpha = 1e-2
times = 100
print(f"goal_prediction={goal_pred}")
label = predict(features, weights)
print(f"*Before training*")
print(f"prediction={label}")
print(f"*After training*")
weights = train(features, weights, goal_pred, times, alpha)
label = predict(features, weights)
print(f"prediction={label}")
print(f"confidence={round(100-(abs(label-goal_pred))*100/(label+goal_pred), 2)}%")
print(f"weights={weights}")
def main():
model=base.loadchkpnt(path)
with open('cat_to_name.json', 'r') as jfil:
cat_to_name = json.load(jfil)
probs = base.predict(image_path, model, topk, gpu)
classes = [cat_to_name[str(ix + 1)] for ix in np.array(probs[1][0])]
probability = np.array(probs[0][0])
i=0
while i < topk:
print("{} has probability: {}".format(classes[i], probability[i]))
i += 1
def do_single(r): global training_x, training_y, testing_x, testing_y wl1, wl2 = doTrain(_g_M, _g_eta, r, _g_T, training_x.copy(), training_y.copy()) eout = predict(wl1, wl2, testing_x.copy(), testing_y.copy()) print "r:", r, ", eout:", eout return r, eout
default='cat_to_name.json')
ap.add_argument(
'image_path',
default='/home/workspace/ImageClassifier/flowers/test/1/image_06752.jpg',
nargs='*',
action="store",
type=str)
inputs = ap.parse_args()
image_path = inputs.image_path
topk = inputs.top_k
device = inputs.gpu
path = inputs.checkpoint
dataloaders, image_datasets = base.load_data()
model = base.load_checkpoint(path)
base.testdata_acc(model, dataloaders, image_datasets, 'test', True)
with open('cat_to_name.json', 'r') as json_file:
cat_to_name = json.load(json_file)
img_tensor = base.process_image(image_path)
probs = base.predict(image_path, model, topk)
print("Image Directory: ", image_path)
print("Predictions probabilities: ", probs)
def do_single(M): global training_x, training_y, testing_x, testing_y wl1, wl2 = doTrain(M, _g_eta, _g_w_value_range, _g_T, training_x.copy(), training_y.copy()) eout = predict(wl1, wl2, testing_x.copy(), testing_y.copy()) return M, eout
