def test_blocks_crf_directional(): # test latent directional CRF on blocks # test that all results are the same as equivalent LatentGridCRF X, Y = toy.generate_blocks(n_samples=1) x, y = X[0], Y[0] pairwise_weights = np.array([0, 0, 0, -4, -4, 0, -4, -4, 0, 0]) unary_weights = np.repeat(np.eye(2), 2, axis=0) w = np.hstack([unary_weights.ravel(), pairwise_weights]) pw_directional = np.array( [0, 0, -4, -4, 0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0, 0, 0, -4, -4, 0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0] ) w_directional = np.hstack([unary_weights.ravel(), pw_directional]) crf = LatentGridCRF(n_labels=2, n_states_per_label=2) directional_crf = LatentDirectionalGridCRF(n_labels=2, n_states_per_label=2) h_hat = crf.inference(x, w) h_hat_d = directional_crf.inference(x, w_directional) assert_array_equal(h_hat, h_hat_d) h = crf.latent(x, y, w) h_d = directional_crf.latent(x, y, w_directional) assert_array_equal(h, h_d) h_hat = crf.loss_augmented_inference(x, y, w) h_hat_d = directional_crf.loss_augmented_inference(x, y, w_directional) assert_array_equal(h_hat, h_hat_d) psi = crf.psi(x, h_hat) psi_d = directional_crf.psi(x, h_hat) assert_array_equal(np.dot(psi, w), np.dot(psi_d, w_directional))
def test_blocks_crf_directional(): # test latent directional CRF on blocks # test that all results are the same as equivalent LatentGridCRF X, Y = generate_blocks(n_samples=1) x, y = X[0], Y[0] pairwise_weights = np.array([0, 0, 0, -4, -4, 0, -4, -4, 0, 0]) unary_weights = np.repeat(np.eye(2), 2, axis=0) w = np.hstack([unary_weights.ravel(), pairwise_weights]) pw_directional = np.array([ 0, 0, -4, -4, 0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0, 0, 0, -4, -4, 0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0 ]) w_directional = np.hstack([unary_weights.ravel(), pw_directional]) crf = LatentGridCRF(n_states_per_label=2, inference_method='lp') crf.initialize(X, Y) directional_crf = LatentDirectionalGridCRF(n_states_per_label=2, inference_method='lp') directional_crf.initialize(X, Y) h_hat = crf.inference(x, w) h_hat_d = directional_crf.inference(x, w_directional) assert_array_equal(h_hat, h_hat_d) h = crf.latent(x, y, w) h_d = directional_crf.latent(x, y, w_directional) assert_array_equal(h, h_d) h_hat = crf.loss_augmented_inference(x, y, w) h_hat_d = directional_crf.loss_augmented_inference(x, y, w_directional) assert_array_equal(h_hat, h_hat_d) joint_feature = crf.joint_feature(x, h_hat) joint_feature_d = directional_crf.joint_feature(x, h_hat) assert_array_equal(np.dot(joint_feature, w), np.dot(joint_feature_d, w_directional))
def test_blocks_crf_unaries(): X, Y = generate_blocks(n_samples=1) x, y = X[0], Y[0] unary_weights = np.repeat(np.eye(2), 2, axis=0) pairwise_weights = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0]) w = np.hstack([unary_weights.ravel(), pairwise_weights]) crf = LatentGridCRF(n_states_per_label=2, n_labels=2, n_features=2) h_hat = crf.inference(x, w) assert_array_equal(h_hat / 2, np.argmax(x, axis=-1))
def test_blocks_crf_unaries(): X, Y = toy.generate_blocks(n_samples=1) x, y = X[0], Y[0] unary_weights = np.repeat(np.eye(2), 2, axis=0) pairwise_weights = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0]) w = np.hstack([unary_weights.ravel(), pairwise_weights]) crf = LatentGridCRF(n_labels=2, n_states_per_label=2) h_hat = crf.inference(x, w) assert_array_equal(h_hat / 2, np.argmax(x, axis=-1))
def test_blocks_crf(): X, Y = generate_blocks(n_samples=1) x, y = X[0], Y[0] pairwise_weights = np.array([0, 0, 0, -4, -4, 0, -4, -4, 0, 0]) unary_weights = np.repeat(np.eye(2), 2, axis=0) w = np.hstack([unary_weights.ravel(), pairwise_weights]) crf = LatentGridCRF(n_states_per_label=2, n_labels=2, n_features=2) h_hat = crf.inference(x, w) assert_array_equal(y, h_hat / 2) h = crf.latent(x, y, w) assert_equal(crf.loss(h, h_hat), 0)
def test_blocks_crf(): X, Y = toy.generate_blocks(n_samples=1) x, y = X[0], Y[0] pairwise_weights = np.array([0, 0, 0, -4, -4, 0, -4, -4, 0, 0]) unary_weights = np.repeat(np.eye(2), 2, axis=0) w = np.hstack([unary_weights.ravel(), pairwise_weights]) crf = LatentGridCRF(n_labels=2, n_states_per_label=2) h_hat = crf.inference(x, w) assert_array_equal(y, h_hat / 2) h = crf.latent(x, y, w) assert_equal(crf.loss(h, h_hat), 0)
def main(): X, Y = toy.generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8) X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5) n_labels = len(np.unique(Y_train)) crf = LatentGridCRF(n_labels=n_labels, n_states_per_label=[1, 2], inference_method='lp') #clf = LatentSSVM(model=crf, max_iter=500, C=1000., verbose=2, #check_constraints=True, n_jobs=-1, break_on_bad=True, #base_svm='1-slack', inference_cache=20, tol=.1) clf = LatentSubgradientSSVM( model=crf, max_iter=500, C=1000., verbose=2, n_jobs=-1, learning_rate=0.1, show_loss_every=10) clf.fit(X_train, Y_train) #for X_, Y_, H, name in [[X_train, Y_train, clf.H_init_, "train"], #[X_test, Y_test, [None] * len(X_test), "test"]]: for X_, Y_, H, name in [[X_train, Y_train, [None] * len(X_test), "train"], [X_test, Y_test, [None] * len(X_test), "test"]]: Y_pred = clf.predict(X_) i = 0 loss = 0 for x, y, h_init, y_pred in zip(X_, Y_, H, Y_pred): loss += np.sum(y != y_pred) fig, ax = plt.subplots(3, 2) ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1) ax[0, 0].set_title("ground truth") ax[0, 1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1) ax[0, 1].set_title("unaries only") if h_init is None: ax[1, 0].set_visible(False) else: ax[1, 0].matshow(h_init, vmin=0, vmax=crf.n_states - 1) ax[1, 0].set_title("latent initial") ax[1, 1].matshow(crf.latent(x, y, clf.w), vmin=0, vmax=crf.n_states - 1) ax[1, 1].set_title("latent final") ax[2, 0].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states - 1) ax[2, 0].set_title("prediction latent") ax[2, 1].matshow(y_pred, vmin=0, vmax=crf.n_labels - 1) ax[2, 1].set_title("prediction") for a in ax.ravel(): a.set_xticks(()) a.set_yticks(()) fig.savefig("data_%s_%03d.png" % (name, i), bbox_inches="tight") i += 1 print("loss %s set: %f" % (name, loss)) print(clf.w)
tol=.1) clf = LatentSSVM(base_ssvm=base_ssvm) clf.fit(X_train, Y_train) print("loss training set: %f" % clf.score(X_train, Y_train)) print("loss test set: %f" % clf.score(X_test, Y_test)) Y_pred = clf.predict(X_test) x, y, y_pred = X_test[1], Y_test[1], Y_pred[1] fig, ax = plt.subplots(3, 2) ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1) ax[0, 0].set_title("ground truth") ax[0, 1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1) ax[0, 1].set_title("unaries only") ax[1, 0].set_visible(False) ax[1, 1].matshow(crf.latent(x, y, clf.w), vmin=0, vmax=crf.n_states - 1) ax[1, 1].set_title("latent final") ax[2, 0].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states - 1) ax[2, 0].set_title("prediction latent") ax[2, 1].matshow(y_pred, vmin=0, vmax=crf.n_labels - 1) ax[2, 1].set_title("prediction") for a in ax.ravel(): a.set_xticks(()) a.set_yticks(()) plt.show()
base_ssvm = OneSlackSSVM(model=crf, C=10., n_jobs=-1, inference_cache=20, tol=.1) clf = LatentSSVM(base_ssvm=base_ssvm) clf.fit(X_train, Y_train) print("Score training set: %f" % clf.score(X_train, Y_train)) print("Score test set: %f" % clf.score(X_test, Y_test)) Y_pred = clf.predict(X_test) x, y, y_pred = X_test[1], Y_test[1], Y_pred[1] fig, ax = plt.subplots(3, 2) ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1) ax[0, 0].set_title("ground truth") ax[0, 1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1) ax[0, 1].set_title("unaries only") ax[1, 0].set_visible(False) ax[1, 1].matshow(crf.latent(x, y, clf.w), vmin=0, vmax=crf.n_states - 1) ax[1, 1].set_title("latent final") ax[2, 0].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states - 1) ax[2, 0].set_title("prediction latent") ax[2, 1].matshow(y_pred, vmin=0, vmax=crf.n_labels - 1) ax[2, 1].set_title("prediction") for a in ax.ravel(): a.set_xticks(()) a.set_yticks(()) plt.show()
tol=.1) clf = LatentSSVM(base_ssvm=base_ssvm) clf.fit(X_train, Y_train) print("Score training set: %f" % clf.score(X_train, Y_train)) print("Score test set: %f" % clf.score(X_test, Y_test)) Y_pred = clf.predict(X_test) x, y, y_pred = X_test[1], Y_test[1], Y_pred[1] fig, ax = plt.subplots(3, 2) ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1) ax[0, 0].set_title("ground truth") ax[0, 1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1) ax[0, 1].set_title("unaries only") ax[1, 0].set_visible(False) ax[1, 1].matshow(crf.latent(x, y, clf.w), vmin=0, vmax=crf.n_states - 1) ax[1, 1].set_title("latent final") ax[2, 0].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states - 1) ax[2, 0].set_title("prediction latent") ax[2, 1].matshow(y_pred, vmin=0, vmax=crf.n_labels - 1) ax[2, 1].set_title("prediction") for a in ax.ravel(): a.set_xticks(()) a.set_yticks(()) plt.show()
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8) X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.5) crf = LatentGridCRF(n_states_per_label=[1, 2]) base_ssvm = OneSlackSSVM(model=crf, C=10.0, n_jobs=-1, inference_cache=20, tol=0.1) clf = LatentSSVM(base_ssvm=base_ssvm) clf.fit(X_train, Y_train) print("loss training set: %f" % clf.score(X_train, Y_train)) print("loss test set: %f" % clf.score(X_test, Y_test)) Y_pred = clf.predict(X_test) x, y, y_pred = X_test[1], Y_test[1], Y_pred[1] fig, ax = plt.subplots(3, 2) ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1) ax[0, 0].set_title("ground truth") ax[0, 1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1) ax[0, 1].set_title("unaries only") ax[1, 0].set_visible(False) ax[1, 1].matshow(crf.latent(x, y, clf.w), vmin=0, vmax=crf.n_states - 1) ax[1, 1].set_title("latent final") ax[2, 0].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states - 1) ax[2, 0].set_title("prediction latent") ax[2, 1].matshow(y_pred, vmin=0, vmax=crf.n_labels - 1) ax[2, 1].set_title("prediction") for a in ax.ravel(): a.set_xticks(()) a.set_yticks(()) plt.show()