location = T.fmatrix() scale = T.fmatrix() alpha = T.fmatrix() x = T.fvector() batch_size = 1 num_channel = 1 patch_shape = (28, 28) image_shape = (100, 100) hyperparameters = {} hyperparameters["cutoff"] = 3000 hyperparameters["batched_window"] = True # tds, _ = get_cooking_streams(batch_size) tds, _ = get_bmnist_streams(1) res = tds.get_epoch_iterator(as_dict=True).next()['features'] # shape: 3 x 125 x 200 img = res[5, 0] draw(img) plt.savefig('img.png') cropper = LocallySoftRectangularCropper(patch_shape=patch_shape, hyperparameters=hyperparameters, kernel=Gaussian()) patch1, matrix, dx2 = cropper.apply( x.reshape(( batch_size, num_channel, ) + image_shape), np.array([list(image_shape)]), location, scale, alpha)
cropper = LocallySoftRectangularCropper( patch_shape=(28, 28), hyperparameters={'cutoff': 3000, 'batched_window': True}, kernel=Gaussian()) down, W, dx2 = cropper.apply( input_, np.array([list((100, 100))]), T.constant( 99 * [[80, 70]]).astype('float32'), T.constant( 99 * [[0.28, 0.28]]).astype('float32'), T.constant( 99 * [[0.001, ] * 2]).astype('float32')) f = theano.function([input_], [down, W, dx2]) data = get_bmnist_streams(99)[0].get_epoch_iterator().next() res = f(data[0][0]) print np.min(res[2][0], axis=0) print np.sum(res[1][0], axis=0) plt.imshow(res[1][0], interpolation='nearest') plt.savefig('w.png') import ipdb; ipdb.set_trace()
# shape: B x C x X x Y input_ = tensor5('features') cropper = LocallySoftRectangularCropper(patch_shape=(28, 28), hyperparameters={ 'cutoff': 3000, 'batched_window': True }, kernel=Gaussian()) down, W, dx2 = cropper.apply( input_, np.array([list((100, 100))]), T.constant(99 * [[80, 70]]).astype('float32'), T.constant(99 * [[0.28, 0.28]]).astype('float32'), T.constant(99 * [[ 0.001, ] * 2]).astype('float32')) f = theano.function([input_], [down, W, dx2]) data = get_bmnist_streams(99)[0].get_epoch_iterator().next() res = f(data[0][0]) print np.min(res[2][0], axis=0) print np.sum(res[1][0], axis=0) plt.imshow(res[1][0], interpolation='nearest') plt.savefig('w.png') import ipdb ipdb.set_trace()
interpolation='nearest') location = T.fmatrix() scale = T.fmatrix() alpha = T.fmatrix() x = T.fvector() batch_size = 1 num_channel = 1 patch_shape = (28, 28) image_shape = (100, 100) hyperparameters = {} hyperparameters["cutoff"] = 3000 hyperparameters["batched_window"] = True # tds, _ = get_cooking_streams(batch_size) tds, _ = get_bmnist_streams(1) res = tds.get_epoch_iterator(as_dict=True).next()['features'] # shape: 3 x 125 x 200 img = res[5, 0] draw(img) plt.savefig('img.png') cropper = LocallySoftRectangularCropper( patch_shape=patch_shape, hyperparameters=hyperparameters, kernel=Gaussian()) patch1, matrix, dx2 = cropper.apply( x.reshape((batch_size, num_channel,) + image_shape), np.array([list(image_shape)]), location,