我们从Python开源项目中，提取了以下14个代码示例，用于说明如何使用tensorflow.extract_image_patches()。
def extract_patches_fn(image: tf.Tensor, patch_shape: list, offsets) -> tf.Tensor: """ :param image: tf.Tensor :param patch_shape: [h, w] :param offsets: tuple between 0 and 1 :return: patches [batch_patches, h, w, c] """ with tf.name_scope('patch_extraction'): h, w = patch_shape c = image.get_shape()[-1] offset_h = tf.cast(tf.round(offsets[0] * h // 2), dtype=tf.int32) offset_w = tf.cast(tf.round(offsets[1] * w // 2), dtype=tf.int32) offset_img = image[offset_h:, offset_w:, :] offset_img = offset_img[None, :, :, :] patches = tf.extract_image_patches(offset_img, ksizes=[1, h, w, 1], strides=[1, h // 2, w // 2, 1], rates=[1, 1, 1, 1], padding='VALID') patches_shape = tf.shape(patches) return tf.reshape(patches, [tf.reduce_prod(patches_shape[0:3]), h, w, int(c)]) # returns [batch_patches, h, w, c]
def extract_image_patches(x, ksizes, ssizes, padding='same', data_format='channels_last'): ''' Extract the patches from an image # Parameters x : The input image ksizes : 2-d tuple with the kernel size ssizes : 2-d tuple with the strides size padding : 'same' or 'valid' data_format : 'channels_last' or 'channels_first' # Returns The (k_w,k_h) patches extracted TF ==> (batch_size,w,h,k_w,k_h,c) TH ==> (batch_size,w,h,c,k_w,k_h) ''' kernel = [1, ksizes[0], ksizes[1], 1] strides = [1, ssizes[0], ssizes[1], 1] padding = _preprocess_padding(padding) if data_format == 'channels_first': x = KTF.permute_dimensions(x, (0, 2, 3, 1)) bs_i, w_i, h_i, ch_i = KTF.int_shape(x) patches = tf.extract_image_patches(x, kernel, strides, [1, 1, 1, 1], padding) # Reshaping to fit Theano bs, w, h, ch = KTF.int_shape(patches) patches = tf.reshape(tf.transpose(tf.reshape(patches, [-1, w, h, tf.floordiv(ch, ch_i), ch_i]), [0, 1, 2, 4, 3]), [-1, w, h, ch_i, ksizes[0], ksizes[1]]) if data_format == 'channels_last': patches = KTF.permute_dimensions(patches, [0, 1, 2, 4, 5, 3]) return patches
def forward(self): inp = self.inp.out s = self.lay.stride self.out = tf.extract_image_patches( inp, [1,s,s,1], [1,s,s,1], [1,1,1,1], 'VALID')
def extract_image_patches(X, ksizes, ssizes, border_mode="same", dim_ordering="tf"): ''' Extract the patches from an image Parameters ---------- X : The input image ksizes : 2-d tuple with the kernel size ssizes : 2-d tuple with the strides size border_mode : 'same' or 'valid' dim_ordering : 'tf' or 'th' Returns ------- The (k_w,k_h) patches extracted TF ==> (batch_size,w,h,k_w,k_h,c) TH ==> (batch_size,w,h,c,k_w,k_h) ''' kernel = [1, ksizes[0], ksizes[1], 1] strides = [1, ssizes[0], ssizes[1], 1] padding = _preprocess_border_mode(border_mode) if dim_ordering == "th": X = KTF.permute_dimensions(X, (0, 2, 3, 1)) bs_i, w_i, h_i, ch_i = KTF.int_shape(X) patches = tf.extract_image_patches(X, kernel, strides, [1, 1, 1, 1], padding) # Reshaping to fit Theano bs, w, h, ch = KTF.int_shape(patches) patches = tf.reshape(tf.transpose(tf.reshape(patches, [bs, w, h, -1, ch_i]), [0, 1, 2, 4, 3]), [bs, w, h, ch_i, ksizes[0], ksizes[1]]) if dim_ordering == "tf": patches = KTF.permute_dimensions(patches, [0, 1, 2, 4, 5, 3]) return patches
def _forward(self, vs): if self.local: # expand input patches and split by filters input_local_expanded = tf.extract_image_patches(self.inpt, pad_shape(self.ksize), self.strides, [1, 1, 1, 1], padding=self.padding) values = [] for filt in tf.split(axis=3, num_or_size_splits=self.n_filters, value=self.filters): channel_i = tf.reduce_sum(tf.multiply(filt, input_local_expanded), 3, keep_dims=True) values.append(channel_i) self.output = tf.concat(axis=3, values=values) else: # split by images in batch and map to regular conv2d function inpt = tf.expand_dims(self.inpt, 1) filt_shape = [-1, self.ksize[0], self.ksize[1], self.n_cin, self.n_filters] filt = tf.reshape(self.filters, filt_shape) elems = (inpt, filt) result = tf.map_fn(lambda x: tf.nn.conv2d(x[0], x[1], self.strides, self.padding), elems, dtype=tf.float32, infer_shape=False) result = tf.squeeze(result, [1]) result.set_shape(self.inpt.get_shape()[:-1].concatenate([self.n_filters])) self.output = result
def _reorg(net, stride): return tf.extract_image_patches( net, [1, stride, stride, 1], [1, stride, stride, 1], [1, 1, 1, 1], 'VALID')
def test_replace_extract_image_patches(self): with self.test_session() as sess: net = tf.random_uniform([2, 26, 26, 128]) net1 = tf.extract_image_patches( net, [1, 2, 2, 1], [1, 2, 2, 1], [1, 1, 1, 1], 'VALID') print(net.get_shape().as_list()) from tensorflow.contrib import slim net2 = slim.conv2d(net, 512, [1, 1], 2) print(net.get_shape().as_list())
def extract_patches(self): image_patches = tf.extract_image_patches(self.input_tensor, ksizes=[1, self.kernel_size,self.kernel_size, 1], strides=[1, self.stride_size,self.stride_size, 1], rates=[1, 1, 1, 1], padding=self.pad) return tf.reshape(image_patches, [self.in_N, self.Hout,self.Wout, self.kernel_size,self.kernel_size, self.in_depth])
def extract_patches(self): image_patches = tf.extract_image_patches(self.input_tensor, ksizes=[1, self.pool_size,self.pool_size, 1], strides=[1, self.stride_size,self.stride_size, 1], rates=[1, 1, 1, 1], padding=self.pad) return tf.reshape(image_patches, [self.in_N, self.Hout,self.Wout, self.pool_size,self.pool_size, self.in_depth])
def pca_ii(ori_image): # Resize particular size ori_image = tf.stack(ori_image) # if dim 3 -> 4 ori_image = tf.expand_dims(ori_image, [0]) ori_image = tf.cast(ori_image, tf.float32) ori_image += 1.0 # Prevent zero divide # Extract uniform k sample ksizes = [1, 1, 1, 1] # 1x1 pixel strides = [1, 10, 10, 1] # 4 rates = [1, 1, 1, 1] sample_pixel = tf.extract_image_patches(ori_image, ksizes, strides, rates, padding='VALID') sample_pixel = tf.squeeze(sample_pixel, [0]) num_sample = sample_pixel.get_shape()[0].value * sample_pixel.get_shape()[1].value sample_pixel = tf.reshape(sample_pixel, [num_sample, 1, 1, 3]) pixel_R = sample_pixel[:,0,0,0] pixel_G = sample_pixel[:,0,0,1] pixel_B = sample_pixel[:,0,0,2] geoM = tf.pow(pixel_R * pixel_G * pixel_B, 1.0/3.0) ch_r = tf.reshape(tf.log(pixel_R / geoM), [1, num_sample]) ch_b = tf.reshape(tf.log(pixel_B / geoM), [1, num_sample]) X = tf.concat([ch_r, ch_b], 0) [U, S, V] = tf.svd(X) vec = S[:,0] alpha = tf.abs(tf.atan(-vec[0] / vec[1])) tmp = tf.squeeze(ori_image, [0]) pixel_R = tmp[:,:,0] pixel_G = tmp[:,:,1] pixel_B = tmp[:,:,2] geoM = tf.pow(pixel_R * pixel_G * pixel_B, 1.0/3.0) num_pixel = ori_image.get_shape()[1].value * ori_image.get_shape()[2].value ch_r = tf.log(pixel_R / geoM) ch_b = tf.log(pixel_B / geoM) ii_image = ch_r * tf.cos(alpha) + ch_b * tf.sin(alpha) return ii_image, alpha
