def evaluate_model():
global model_fname
loader = FileLoader(
dir_to_walk=r'C:\Users\Ivo Ribeiro\Documents\open-cv\datasets\captures'
)
loader.load_files()
x = []
y = []
x_test = []
y_test = []
for row in loader.files:
for fname in row['imgs_per_class']:
img = cv2.imread(fname)
descr = getDescriptor(img)
x.append(descr)
y.append(hot_encode_vect(len(loader.files), row['index']))
for row in loader.files_test:
for fname in row['imgs_per_class']:
img = cv2.imread(fname)
descr = getDescriptor(img)
x_test.append(descr)
y_test.append(hot_encode_vect(len(loader.files_test),
row['index']))
x = np.array(x)
y = np.array(y)
x_test = np.array(x_test)
y_test = np.array(y_test)
print('descriptors loaded.')
print(loader.class_names)
ann = MyAnn(input_layer_size=x.shape[1],
hidden_nodes_size=[x.shape[1] // 4],
output_layer_size=3,
epochs=1000,
ann_fname=model_fname)
ann.fit(x=x, y=y)
print('finished train or load.')
print('evaluating')
corrects = 0
for i in np.arange(x_test.shape[0]):
x = x_test[i]
y = np.argmax(y_test[i])
p, stats = ann.predict(x)
p = int(p)
y = int(y)
stats = np.squeeze(stats)
print('%s predicted as %s with %.2f' %
(loader.class_names[y], loader.class_names[p], stats[p]))
print(stats)
if p == y:
corrects += 1
print('acc %.2f%s' % ((corrects / x_test.shape[0]) * 100, '%'))
def realtime_teste():
global model_fname
ann = MyAnn(input_layer_size=256,
hidden_nodes_size=[256 // 4],
output_layer_size=3,
epochs=1000,
ann_fname=model_fname)
class_names = ['fermento', 'leite_caixa', 'leite_lata']
capture = cv2.VideoCapture(0)
success, frame = capture.read()
center_pt = (frame.shape[1] // 2, frame.shape[0] // 2)
x_center, y_center = center_pt
curr_rect = None
i = 0
for curr_rect in middleRects(frame.shape,
center_x=x_center,
center_y=y_center):
if i == 2:
break
i += 1
while (success):
frame_cpy = frame.copy()
cv2.circle(frame_cpy, (x_center, y_center), 10, (0, 255, 255), 1)
k = cv2.waitKey(5)
if k == ord('q'):
break
success, frame = capture.read()
x, y, w, h = curr_rect
cv2.rectangle(frame_cpy, (x, y), (x + w, y + h), (0, 255, 0), 2)
roi = frame[y:y + h, x:x + w]
descr = getDescriptor(roi)
_, stats = ann.predict(descr)
stats = np.squeeze(stats)
txt = ('label %s with %.2f' % (class_names[0], stats[0]))
cv2.putText(frame_cpy, txt, (25, 25), cv2.FONT_HERSHEY_COMPLEX, 1,
(255, 0, 0), 1)
txt = ('label %s with %.2f' % (class_names[1], stats[1]))
cv2.putText(frame_cpy, txt, (25, 50), cv2.FONT_HERSHEY_COMPLEX, 1,
(0, 255, 0), 1)
txt = ('label %s with %.2f' % (class_names[2], stats[2]))
cv2.putText(frame_cpy, txt, (25, 75), cv2.FONT_HERSHEY_COMPLEX, 1,
(0, 0, 255), 1)
txt = 'soma %.2f' % (np.sum(stats))
cv2.putText(frame_cpy, txt, (25, 100), cv2.FONT_HERSHEY_COMPLEX, 1,
(0, 255, 255), 1)
cv2.imshow('', frame_cpy)
capture.release()
cv2.destroyAllWindows()
def train_knn(self):
responses = []
descriptors = []
for row in self.files:
dirs = row['imgs_per_class']
idx = row['index']
for file_name in dirs:
descriptor = getDescriptor( cv2.imread(file_name,cv2.IMREAD_GRAYSCALE),self.shape)
descriptors.append(descriptor)
responses.append(idx)
print('training')
descriptors = np.squeeze(descriptors)
self.train(
np.array(descriptors,dtype=np.float32),
np.array(responses,dtype=np.float32)
)
print('trained')
def chart_data():
loader = FileLoader(r'C:\Users\Ivo Ribeiro\Documents\open-cv\datasets\captures')
loader.load_files()
seed = 11
tsne = TSNE(n_components=2,random_state=seed)
fig = plt.figure()
ax = fig.add_subplot(111)
colors = ['b','g','r'] #3 classes
all_features = []
all_labels = []
all_class_names = []
for row in loader.files:
imgs_fnames = row['imgs_per_class']
features = []
labels = []
class_names = []
for f_name in imgs_fnames:
img = cv2.imread(f_name)
descr = getDescriptor(img,expected_shape=(128,64))
features.append(descr)
labels.append(row['index'])
class_names.append(row['class_name'])
row['features'] = np.array(features)
all_features.extend(features)
all_labels.extend(labels)
all_class_names.extend(class_names)
all_features = np.array(all_features)
all_labels = np.array(all_labels)
stds = np.std(all_features,axis=0)
all_features = all_features[:,stds > 0.0003]
print(all_features.shape)
print(all_labels.shape)
for label,label_name in zip(np.unique(all_labels),np.unique(all_class_names)):
features = all_features[ all_labels==label ,:]
transformed = tsne.fit_transform(features)
ax.scatter(x=transformed[:,0],y=transformed[:,1],c=colors[label],label=label_name)
plt.title('captures dataset')
ax.legend(loc='best')
plt.show()
def show_std():
knn = Knn()
knn.run()
if knn.loaded:
knn.load_files()
descriptors = []
for row in knn.files:
imgs = row['imgs_per_class']
for fname in imgs:
descriptors.append( getDescriptor( cv2.imread(fname , cv2.IMREAD_GRAYSCALE) ),knn.shape )
descriptors = np.array(descriptors)
stds = np.std(descriptors,axis=0)
stds = stds * 100
stds = np.int8(stds)
min_bin = np.min(stds)
max_bin = np.max(stds)
bins = (max_bin-min_bin)
hist = np.histogram(stds,bins=bins)
hist = hist[0]
plt.figure(0)
plt.title('std (> better)')
ranges = np.linspace(min_bin,max_bin,bins)
plt.bar(ranges,hist)
plt.show()
def processAndPredict(self,sample , k = 6):
descriptor = getDescriptor(sample,self.shape)
return self.knn.findNearest(np.array([descriptor],dtype=np.float32), k)