def predict(self, record):
with self.graph.as_default():
with self.session.as_default():
indices = np.r_[0:6]
X = np.transpose(
np.transpose(self.test_dict[record]["x"])[indices][:][:])
# X = self.test_dict[record]["x"]
X = np.expand_dims(X, 0)
X = np.expand_dims(X, 0)
X = rescale_array(X)
# print(X.shape)
Y_pred = self.model.predict(X)
all_rows = []
# print(Y_pred.shape)
for i in range(len(Y_pred[0][0])):
row = {}
row["sleepstage"] = mapping[i]
row["value"] = Y_pred[0][0][i]
all_rows.append(row)
with open('../frontend/data/SleepProb.json', 'w') as f:
f.write(
str(all_rows).replace('\'',
'"').replace('None', 'null'))
grads = visualization.visualize_saliency(self.model,
-2,
filter_indices=None,
seed_input=X)
# print("Predicted values", Y_pred)
Y_pred = Y_pred.argmax(axis=-1)
return grads, Y_pred[0]
def update_image(self, fft_array, factor=None):
scaled_values, sf = rescale_array(np.real(np.log2(fft_array)),
self.scale_factor)
self.scale_factor = sf
self.image = array_to_image(scaled_values)
self.setMinimumSize(self.image.size())
self.overlay.resize(self.image.size())
self.update()
self.updateGeometry()
# I have to deliver, and it's broken on windows.
self.setMinimumSize(self.image.size())
self.overlay.resize(self.image.size())
self.update()
self.updateGeometry()
def pred_alt(X):
preds = []
gt = []
for record in test_dict:
all_rows = test_dict[record]['x']
record_y_gt = []
record_y_pred = []
for batch_hyp in chunker(range(all_rows.shape[0])):
X = all_rows[min(batch_hyp):max(batch_hyp)+1, ...]
Y = test_dict[record]['y'][min(batch_hyp):max(batch_hyp)+1]
X = np.expand_dims(X, 0)
X = rescale_array(X)
Y_pred = model.predict(X)
Y_pred = Y_pred.argmax(axis=-1).ravel().tolist()
gt += Y.ravel().tolist()
preds += Y_pred
record_y_gt += Y.ravel().tolist()
record_y_pred += Y_pred
# fig_1 = plt.figure(figsize=(12, 6))
# plt.plot(record_y_gt)
# plt.title("Sleep Stages")
# plt.ylabel("Classes")
# plt.xlabel("Time")
# plt.show()
#
# fig_2 = plt.figure(figsize=(12, 6))
# plt.plot(record_y_pred)
# plt.title("Predicted Sleep Stages")
# plt.ylabel("Classes")
# plt.xlabel("Time")
# plt.show()
return preds
validation_steps=300,
callbacks=callbacks_list)
model.load_weights(file_path)
for record in tqdm(test_dict):
all_rows = test_dict[record]['x']
record_y_gt = []
record_y_pred = []
for batch_hyp in chunker(range(all_rows.shape[0])):
X = all_rows[min(batch_hyp):max(batch_hyp) + 1, ...]
Y = test_dict[record]['y'][min(batch_hyp):max(batch_hyp) + 1]
X = np.expand_dims(X, 0)
X = rescale_array(X)
Y_pred = model.predict(X)
Y_pred = Y_pred.argmax(axis=-1).ravel().tolist()
gt += Y.ravel().tolist()
preds += Y_pred
record_y_gt += Y.ravel().tolist()
record_y_pred += Y_pred
f1 = f1_score(gt, preds, average="macro")
acc = accuracy_score(gt, preds)
print("acc %s, f1 %s" % (acc, f1))