我们从Python开源项目中，提取了以下34个代码示例，用于说明如何使用keras.applications.vgg16.preprocess_input()。
def preprocess_image_crop(image_path, img_size): ''' Preprocess the image scaling it so that its smaller size is img_size. The larger size is then cropped in order to produce a square image. ''' img = load_img(image_path) scale = float(img_size) / min(img.size) new_size = (int(np.ceil(scale * img.size[0])), int(np.ceil(scale * img.size[1]))) # print('old size: %s,new size: %s' %(str(img.size), str(new_size))) img = img.resize(new_size, resample=Image.BILINEAR) img = img_to_array(img) crop_h = img.shape[0] - img_size crop_v = img.shape[1] - img_size img = img[crop_h:img_size+crop_h, crop_v:img_size+crop_v, :] img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img # util function to open, resize and format pictures into appropriate tensors
def preprocess_image_scale(image_path, img_size=None): ''' Preprocess the image scaling it so that its larger size is max_size. This function preserves aspect ratio. ''' img = load_img(image_path) if img_size: scale = float(img_size) / max(img.size) new_size = (int(np.ceil(scale * img.size[0])), int(np.ceil(scale * img.size[1]))) img = img.resize(new_size, resample=Image.BILINEAR) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img # util function to convert a tensor into a valid image
def extract_vgg16_features(x): from keras.preprocessing.image import img_to_array, array_to_img from keras.applications.vgg16 import preprocess_input, VGG16 from keras.models import Model # im_h = x.shape[1] im_h = 224 model = VGG16(include_top=True, weights='imagenet', input_shape=(im_h, im_h, 3)) # if flatten: # add_layer = Flatten() # else: # add_layer = GlobalMaxPool2D() # feature_model = Model(model.input, add_layer(model.output)) feature_model = Model(model.input, model.get_layer('fc1').output) print('extracting features...') x = np.asarray([img_to_array(array_to_img(im, scale=False).resize((im_h,im_h))) for im in x]) x = preprocess_input(x) # data - 127. #data/255.# features = feature_model.predict(x) print('Features shape = ', features.shape) return features
def preprocess(img): img4d = img.copy() img4d = img4d.astype("float64") if K.image_dim_ordering() == "th": # (H, W, C) -> (C, H, W) img4d = img4d.transpose((2, 0, 1)) img4d = np.expand_dims(img4d, axis=0) img4d = vgg16.preprocess_input(img4d) return img4d
def preprocessImage(imagePath): img = load_img(imagePath, target_size=(244, 244)) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) img = img.reshape(img.shape[1:]) return img
def preprocess_image(image_path): img = load_img(image_path, target_size=(im_height, im_width)) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img
def get_features(url): response = requests.get(url) img = Image.open(BytesIO(response.content)).convert('RGB') target_size = (224, 224) model = VGG16(weights='imagenet', include_top=False, pooling='avg') if img.size != target_size: img = img.resize(target_size) x = image.img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x) features = model.predict(x).flatten() return features.tolist()
def preprocess_image(image_path): img = load_img(image_path, target_size=(img_nrows, img_ncols)) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img # util function to convert a tensor into a valid image
def preprocess_image(image_path): img = load_img(image_path, target_size=(img_width, img_height)) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img # util function to convert a tensor into a valid image
def preprocess_input(x): return vgg16.preprocess_input(x.astype('float32'))
def import_vgg16(): global VGG16 global Model global image global preprocess_input global K from keras.applications import VGG16 from keras.models import Model from keras.preprocessing import image from keras.applications.vgg16 import preprocess_input from keras import backend as K if K.backend() == 'tensorflow': limit_mem()
def imread(self, path): if 'http' == path[:4]: with contextlib.closing(urllib.urlopen(path)) as req: local_url = cStringIO.StringIO(req.read()) img = image.load_img(local_url, target_size=(self.target_dim, self.target_dim)) else: img = image.load_img(path, target_size=(self.target_dim, self.target_dim)) img = image.img_to_array(img) img = np.expand_dims(img, axis=0) img = preprocess_input(img) return img
def preprocess_image(image_path): img = load_img(image_path, target_size=(img_nrows, img_ncols)) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img
def load_image(path): img_path = path img = load_img(img_path, target_size=(299, 299)) x = img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x) return x
def load_data(path, size=224, mode=None): img = Image.open(path) w,h = img.size if w < h: if w < size: img = img.resize((size, size*h//w)) w, h = img.size else: if h < size: img = img.resize((size*w//h, size)) w, h = img.size img = img.crop((int((w-size)*0.5), int((h-size)*0.5), int((w+size)*0.5), int((h+size)*0.5))) if mode=="original": return img if mode=="label": y = np.array(img, dtype=np.int32) mask = y == 255 y[mask] = 0 y = binarylab(y, size, 21) y = np.expand_dims(y, axis=0) return y if mode=="data": X = image.img_to_array(img) X = np.expand_dims(X, axis=0) X = preprocess_input(X) return X
def preprocess_image(image_path, desired_dims): img = load_img(image_path, target_size=desired_dims) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img # util function to convert a tensor into a valid image
def extract_feat(img_path): # weights: 'imagenet' # pooling: 'max' or 'avg' # input_shape: (width, height, 3), width and height should >= 48 input_shape = (224, 224, 3) model = VGG16(weights = 'imagenet', input_shape = (input_shape[0], input_shape[1], input_shape[2]), pooling = 'max', include_top = False) img = image.load_img(img_path, target_size=(input_shape[0], input_shape[1])) img = image.img_to_array(img) img = np.expand_dims(img, axis=0) img = preprocess_input(img) feat = model.predict(img) norm_feat = feat[0]/LA.norm(feat[0]) return norm_feat
def extract_image_features(img_path): model = models.VGG_16('weights/vgg16_weights.h5') img = image.load_img(img_path,target_size=(224,224)) x = image.img_to_array(img) x = np.expand_dims(x,axis=0) x = preprocess_input(x) last_layer_output = K.function([model.layers[0].input,K.learning_phase()], [model.layers[-1].input]) features = last_layer_output([x,0])[0] return features
def preprocess_image(image_path): img = load_img(image_path, target_size=(img_height, img_width)) img = img_to_array(img) img = np.expand_dims(img, axis=0) img = vgg16.preprocess_input(img) return img # util function to convert a tensor into a valid image
def preprocess_image(filename, target_size): img = image.load_img(filename, target_size=target_size) x = image.img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x) x = np.squeeze(x) return x
def drawbbox(self, img, xx, testmodel, confid_thresh, w, h, c): ttimg, x0_list, y0_list, x1_list, y1_list, classprob_list, class_id_list, confid_value_list = utils.predict(preprocess_input(np.asarray([xx])), testmodel, confid_thresh,w,h,c) for x0,y0,x1,y1,classprob,class_id,confid_value in zip(x0_list, y0_list, x1_list, y1_list, classprob_list, class_id_list, confid_value_list): # draw bounding box cv2.rectangle(img, (x0, y0), (x1, y1), (255,255,255), 2) # draw classimg classimg = cv2.imread(cfgconst.label_names[class_id]) if y0-classimg.shape[0] <= 0: yst =0 yend =classimg.shape[0] elif y0 >= img.shape[0]: yst = img.shape[0]-classimg.shape[0]-1 yend = img.shape[0]-1 else: yst = y0 - classimg.shape[0] yend = y0 if x0+classimg.shape[1] >= img.shape[1]: xst = img.shape[1]-classimg.shape[1]-1 xend = img.shape[1]-1 elif x0 <=0: xst = 0 xend = classimg.shape[1] else: xst = x0 xend = x0+classimg.shape[1] # img[yst:yend, xst:xend] = classimg # draw text font = cv2.FONT_HERSHEY_SIMPLEX cv2.putText(img, str(classprob), (x0,y0+classimg.shape[0]-1), font, 0.5,(255,255,255),2,cv2.LINE_AA) cv2.putText(img, str(confid_value), (x0,y1), font, 0.5,(128,255,255),1,cv2.LINE_AA) # cv2.imshow('frame',img) cv2.waitKey(1)
def testonefile(testmodel, img_path, confid_thresh=0.3, fordebug=False ): (s,w,h,c) = testmodel.layers[0].input_shape fimg, sx, sy, dx, dy, flip,ssx,ssy = genregiontruth_bnum.crop_image(img_path.strip(), w, h, randomize=False) xx = fimg.copy() img = fimg.astype(float) if fordebug: # read label fn=img_path.replace("/JPEGImages/","/labels/") fn=fn.replace(".jpg",".txt") #VOC boxlist = genregiontruth_bnum.readlabel(fn.strip(), sx, sy, dx, dy, flip, ssx, ssy) for box in boxlist: draw.rectangle([(box.x-box.w/2)*w,(box.y-box.h/2)*h,(box.x+box.w/2)*w,(box.y+box.h/2)*h]) # ttimg, x0_list, y0_list, x1_list, y1_list, classprob_list, class_id_list, confid_value_list = predict(preprocess_input(np.asarray([xx])), testmodel, confid_thresh,w,h,c) iimg = Image.fromarray(img.astype(np.uint8)) draw = ImageDraw.Draw(iimg, 'RGBA') sortedindexlist = np.argsort(confid_value_list) colors=[] for i in range(3): for j in range(7): if i==0: rcolor = (j+1)*32 gcolor = 0 bcolor = 0 elif i==1: rcolor = 0 gcolor = (j+1)*32 bcolor = 0 else: rcolor = 0 gcolor = 0 bcolor = (j+1)*32 colors.append( (rcolor, gcolor, bcolor, 127) ) #print colors for i in range(len(confid_value_list)): index = sortedindexlist[len(confid_value_list)-i-1] for k in range(5): # thick line draw.rectangle([x0_list[index]+k,y0_list[index]+k,x1_list[index]-k,y1_list[index]-k], outline=colors[class_id_list[index]]) labelim = Image.open(cfgconst.label_names[class_id_list[index]]) draw.bitmap((x0_list[index],y0_list[index]),labelim) x = (x0_list[index]+x1_list[index])/2. y = (y0_list[index]+y1_list[index])/2. x0 = int(x/w*cfgconst.side)*w/cfgconst.side y0 = int(y/h*cfgconst.side)*h/cfgconst.side x1 = x0 + float(w)/cfgconst.side y1 = y0 + float(h)/cfgconst.side draw.rectangle([x0,y0,x1,y1], fill=colors[class_id_list[index]] ) print cfgconst.label_names[class_id_list[index]].split('/')[1].split('.')[0]+': '+str(confid_value_list[index]) del draw iimg.save('predicted.png')
def testvideo(testmodel, videofile, confid_thresh=0.2): print 'testdemo '+videofile #testmodel = load_model(model_weights_path, custom_objects={'yololoss': ddd.yololoss}) (s,w,h,c) = testmodel.layers[0].input_shape cap = cv2.VideoCapture(videofile) while (cap.isOpened()): ret, frame = cap.read() if not ret: break #print frame nim = scipy.misc.imresize(frame, (w, h, c)) img = nim xx = image.img_to_array(cv2.cvtColor(nim, cv2.COLOR_RGB2BGR)) ttimg, x0_list, y0_list, x1_list, y1_list, classprob_list, class_id_list, confid_value_list = predict(preprocess_input(np.asarray([xx])), testmodel, confid_thresh,w,h,c) # found confid box for x0,y0,x1,y1,classprob,class_id,confid_value in zip(x0_list, y0_list, x1_list, y1_list, classprob_list, class_id_list, confid_value_list): # # draw bounding box cv2.rectangle(img, (x0, y0), (x1, y1), (255,255,255), 2) # draw classimg classimg = cv2.imread(cfgconst.label_names[class_id]) if y0-classimg.shape[0] <= 0: yst =0 yend =classimg.shape[0] elif y0 >= img.shape[0]: yst = img.shape[0]-classimg.shape[0]-1 yend = img.shape[0]-1 else: yst = y0 - classimg.shape[0] yend = y0 if x0+classimg.shape[1] >= img.shape[1]: xst = img.shape[1]-classimg.shape[1]-1 xend = img.shape[1]-1 elif x0 <=0: xst = 0 xend = classimg.shape[1] else: xst = x0 xend = x0+classimg.shape[1] # img[yst:yend, xst:xend] = classimg # draw text font = cv2.FONT_HERSHEY_SIMPLEX cv2.putText(img, str(classprob), (x0,y0+classimg.shape[0]-1), font, 0.5,(255,255,255),2,cv2.LINE_AA) cv2.putText(img, str(confid_value), (x0,y1), font, 0.5,(128,255,255),1,cv2.LINE_AA) # cv2.imshow('frame',img) if cv2.waitKey(100) & 0xFF == ord('q'): break cap.release() cv2.destroyAllWindows()
