def plot_multiple_models(images):
model_name = 'syn_model'
fig, axs = plt.subplots(3,3)
fig.suptitle('Linear ranges for multiple models')
# Some example data to display
x = np.linspace(0, 2 * np.pi, 400)
y = np.sin(x ** 2)
iter = 0
for i in range(3):
for j in range(3):
model = FourLayerFNN()
model.load_state_dict(torch.load(model_name+str(iter)+'.pkl'))
for image in images:
image = image.view(-1, 2)
coefficients_file_name = calculate_ineuqality_coefficients(model, image)
calculate_feasible_range(coefficients_file_name, axs[i][j])
axs[i][j].set_xlim((-1.5, 1.5))
axs[i][j].set_ylim((-1.5, 1.5))
axs[i][j].set_title('model'+str(iter))
axs[i][j].set(xlabel='x', ylabel='y')
axs[i][j].label_outer()
plot_unit_circle(axs[i][j])
iter += 1
plt.show()
def plot_multiple_models(x, images):
model_name = 'syn_model'
models = []
fig, axes = plt.subplots(3, 3)
fig.suptitle('Linear ranges for multiple models')
for i, ax in enumerate(axes.flat):
model = FourLayerFNN()
model.load_state_dict(torch.load(model_name + str(i) + '.pkl'))
plot_one_model(ax, model, x, images)
ax.set(xlabel='x', ylabel='y')
ax.set_xlim((-1.5, 1.5))
ax.set_ylim((-1.5, 1.5))
ax.set_title('model' + str(i))
ax.label_outer()
plt.show()
def plot_lines(weight_bias_states):
for row in weight_bias_states[:3, :]:
a, b, c, _ = row
# print('a: ', a, '; b:', b, '; c:', c)
plot_line(a, b, c)
def plot_line(a, b, c):
x = np.linspace(-1.5, 1.5, 1000)
y = -(a * x + c) / b
plt.plot(x, y)
if __name__ == '__main__':
model = FourLayerFNN()
model.load_state_dict(torch.load('syn_model.pkl'))
# load test data, here is same to train_data
test_loader = torch.utils.data.DataLoader(MyCustomDataset(
'./data/dataset.csv',
transform=transforms.Compose([transforms.ToTensor()])),
batch_size=1,
shuffle=True)
# test(model, test_loader)
images = test_loader.dataset.images
# print(image.shape)
# _, outputs = model(image)
# _, prediction = torch.max(outputs.data, 1)
# print(prediction)
# check_states(model, image)