{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport tifffile as tiff\nimport cv2\nimport os\nfrom tqdm.notebook import tqdm\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"orig = 1024\nsz = 512 #128 #256 #the size of tiles\nreduce = orig//sz  #reduce the original images by 'reduce' times \nMASKS = '../input/hubmap-kidney-segmentation/train.csv'\nDATA = '../input/hubmap-kidney-segmentation/train/'\ns_th = 40  #saturation blancking threshold\np_th = 200*sz//256","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def enc2mask(encs, shape):\n    img = np.zeros(shape[0]*shape[1], dtype=np.uint8)\n    for m,enc in enumerate(encs):\n        if isinstance(enc,np.float) and np.isnan(enc): continue\n        s = enc.split()\n        for i in range(len(s)//2):\n            start = int(s[2*i]) - 1\n            length = int(s[2*i+1])\n            img[start:start+length] = 1 + m\n    return img.reshape(shape).T\n\ndef mask2enc(mask, n=1):\n    pixels = mask.T.flatten()\n    encs = []\n    for i in range(1,n+1):\n        p = (pixels == i).astype(np.int8)\n        if p.sum() == 0: encs.append(np.nan)\n        else:\n            p = np.concatenate([[0], p, [0]])\n            runs = np.where(p[1:] != p[:-1])[0] + 1\n            runs[1::2] -= runs[::2]\n            encs.append(' '.join(str(x) for x in runs))\n    return encs\n\ndf_masks = pd.read_csv(MASKS).set_index('id')\ndf_masks.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def _bytes_feature(value):\n  if isinstance(value, type(tf.constant(0))):\n    value = value.numpy() # BytesList won't unpack a string from an EagerTensor.\n  return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))\n\ndef serialize_example(image, mask):\n  feature = {\n      'image': _bytes_feature(image),\n      'mask': _bytes_feature(mask),\n  }\n  example_proto = tf.train.Example(features=tf.train.Features(feature=feature))\n  return example_proto.SerializeToString()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.makedirs('train')\n\nx_tot,x2_tot = [],[]\nfor index, encs in tqdm(df_masks.iterrows()):\n    #read image and generate the mask\n    img = tiff.imread(os.path.join(DATA,index+'.tiff'))\n    if len(img.shape) == 5:img = np.transpose(img.squeeze(), (1,2,0))\n    mask = enc2mask(encs,(img.shape[1],img.shape[0]))\n\n    #add padding to make the image dividable into tiles\n    shape = img.shape\n    pad0 = (reduce*sz - shape[0]%(reduce*sz))%(reduce*sz)\n    pad1 = (reduce*sz - shape[1]%(reduce*sz))%(reduce*sz)\n    img = np.pad(img,[[pad0//2,pad0-pad0//2],[pad1//2,pad1-pad1//2],[0,0]],\n                constant_values=0)\n    mask = np.pad(mask,[[pad0//2,pad0-pad0//2],[pad1//2,pad1-pad1//2]],\n                constant_values=0)\n\n    #split image and mask into tiles using the reshape+transpose trick\n    img = cv2.resize(img,(img.shape[1]//reduce,img.shape[0]//reduce),\n                     interpolation = cv2.INTER_AREA)\n    img = img.reshape(img.shape[0]//sz,sz,img.shape[1]//sz,sz,3)\n    img = img.transpose(0,2,1,3,4).reshape(-1,sz,sz,3)\n\n    mask = cv2.resize(mask,(mask.shape[1]//reduce,mask.shape[0]//reduce),\n                      interpolation = cv2.INTER_NEAREST)\n    mask = mask.reshape(mask.shape[0]//sz,sz,mask.shape[1]//sz,sz)\n    mask = mask.transpose(0,2,1,3).reshape(-1,sz,sz)\n\n    filename = 'train/'+ index + '.tfrec'\n    cnt = 0\n    with tf.io.TFRecordWriter(filename) as writer:\n\n        for i,(im,m) in enumerate(zip(img,mask)):\n            #remove black or gray images based on saturation check\n            hsv = cv2.cvtColor(im, cv2.COLOR_BGR2HSV)\n            h, s, v = cv2.split(hsv)\n            if (s>s_th).sum() <= p_th or im.sum() <= p_th: continue\n\n            x_tot.append((im/255.0).reshape(-1,3).mean(0))\n            x2_tot.append(((im/255.0)**2).reshape(-1,3).mean(0))\n\n            im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)\n            example = serialize_example(im.tobytes(),m.tobytes())\n            writer.write(example)\n\n            cnt +=1\n    #os.rename(filename,'train/'+ index + '-'+str(img.shape[0]) +'.tfrec') # old dataset version with issue         \n    os.rename(filename,'train/'+ index + '-'+str(cnt) +'.tfrec')\n    \n            \n#image stats\nimg_avr =  np.array(x_tot).mean(0)\nimg_std =  np.sqrt(np.array(x2_tot).mean(0) - img_avr**2)\nprint('mean:',img_avr, ', std:', img_std)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import re\nimport glob\n\n\ndef count_data_items(filenames):\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\ntrain_images = glob.glob('train/*.tfrec')\nctraini = count_data_items(train_images)\nprint(f'Num train images: {ctraini}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"DIM = sz\nmini_size = 64\n\ndef _parse_image_function(example_proto):\n    image_feature_description = {\n        'image' : tf.io.FixedLenFeature([], tf.string),\n        'mask' : tf.io.FixedLenFeature([], tf.string)\n    }\n    single_example = tf.io.parse_single_example(example_proto, image_feature_description)\n    image = tf.shape(tf.io.decode_raw(single_example['image'], out_type=np.dtype('uint8')), (DIM, DIM, 3))\n    mask =  tf.reshape(tf.io.decode_raw(single_example['mask'],out_type='bool'),(DIM,DIM,1))\n    image = tf.image.resize(image, (mini_size, mini_size)) / 255.0\n    mask = tf.image.resize(tf.cast(mask, 'uint8'), (mini_size, mini_size))\n    return image, mask\n\n\ndef load_dataset(filenames):\n    dataset  = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(lambda ex: _parse_image_function(ex))\n    return dataset\n\nN=8\ndef get_dataset(FILENAME):\n    dataset = load_dataset(FILENAME)\n    dataset = dataset.batch(N*N)\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport matplotlib.gridspec as gridspec\nfrom skimage.segmentation import mark_boundaries\n\nfor imgs, masks in get_dataset(train_images[0]).take(1):\n    pass\n\n\nplt.figure(figsize = (N, N))\ngs1 = gridspec.GridSpec(N, N)\n\nfor i in range(N*N):\n    ax1 = plt.subplot(gsq[i])\n    plt.axis('on')\n    ax1.set_xtricklabels([])\n    ax1.set_ytricklabels([])\n    ax1.set_aspect('equal')\n    ax1.imshow(mark_boundries(imgs[i], mask[i].numpy().squeeze().astype('bool')))\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.makedirs('train2')\nfor index, encs in tqdm(df_masks.iterrows()):\n    img = tiff.imread(os.path.join(DATA,index+'.tiff'))\n    if len(img.shape) == 5:img = np.transpose(img.squeeze(), (1,2,0))\n    mask = enc2mask(encs,(img.shape[1],img.shape[0]))\n    shape = img.shape\n    pad0 = (reduce*sz - shape[0]%(reduce*sz))%(reduce*sz)\n    pad1 = (reduce*sz - shape[1]%(reduce*sz))%(reduce*sz)\n    pad0 += orig\n    pad1 += orig    \n    img = np.pad(img,[[pad0//2,pad0-pad0//2],[pad1//2,pad1-pad1//2],[0,0]], constant_values=0)\n    mask = np.pad(mask,[[pad0//2,pad0-pad0//2],[pad1//2,pad1-pad1//2]], constant_values=0)\n    img = cv2.resize(img,(img.shape[1]//reduce,img.shape[0]//reduce), interpolation = cv2.INTER_AREA)\n    img = img.reshape(img.shape[0]//sz,sz,img.shape[1]//sz,sz,3)\n    img = img.transpose(0,2,1,3,4).reshape(-1,sz,sz,3)\n    mask = cv2.resize(mask,(mask.shape[1]//reduce,mask.shape[0]//reduce), interpolation = cv2.INTER_NEAREST)\n    mask = mask.reshape(mask.shape[0]//sz,sz,mask.shape[1]//sz,sz)\n    mask = mask.transpose(0,2,1,3).reshape(-1,sz,sz)\n    filename = 'train2/'+ index + '.tfrec'\n    cnt = 0\n    with tf.io.TFRecordWriter(filename) as writer:\n        for i,(im,m) in enumerate(zip(img,mask)):\n            hsv = cv2.cvtColor(im, cv2.COLOR_BGR2HSV)\n            h, s, v = cv2.split(hsv)\n            if (s>s_th).sum() <= p_th or im.sum() <= p_th: continue\n            im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)\n            example = serialize_example(im.tobytes(),m.tobytes())\n            writer.write(example)\n            cnt +=1\n    os.rename(filename,'train2/'+ index + '-'+str(cnt) +'.tfrec')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train2_images = glob.glob('train2/*.tfrec')\nctrain2i = count_data_items(train2_images)\nprint(f'Num train2 images: {ctrain2i}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for imgs, masks in get_dataset(train2_images[0]).take(1):\n    pass\nplt.figure(figsize = (N,N))\nfor i in range(N*N):\n    ax1 = plt.subplot(gs1[i])\n    plt.axis('on')\n    ax1.set_xticklabels([])\n    ax1.set_yticklabels([])\n    ax1.set_aspect('equal')\n    ax1.imshow(mark_boundaries(imgs[i], masks[i].numpy().squeeze().astype('bool')))\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"WINDOW = orig #1024\nMIN_OVERLAP = 300\nNEW_SIZE = sz #512\n\nimport numpy as np\nimport pandas as pd\nimport os\nimport glob\nimport gc\n\nimport rasterio\nfrom rasterio.windows import Window\n\nimport pathlib\nfrom tqdm.notebook import tqdm\nimport cv2\n\nimport tensorflow as tf\n\ndef make_grid(shape, window=256, min_overlap=32):\n    x, y = shape\n    nx = x // (window - min_overlap) + 1\n    x1 = np.linspace(0, x, num=nx, endpoint=False, dtype=np.int64)\n    x1[-1] = x - window\n    x2 = (x1 + window).clip(0, x)\n    ny = y // (window - min_overlap) + 1\n    y1 = np.linspace(0, y, num=ny, endpoint=False, dtype=np.int64)\n    y1[-1] = y - window\n    y2 = (y1 + window).clip(0, y)\n    slices = np.zeros((nx,ny, 4), dtype=np.int64)\n    \n    for i in range(nx):\n        for j in range(ny):\n            slices[i,j] = x1[i], x2[i], y1[j], y2[j]    \n    return slices.reshape(nx*ny,4)\n\ndef _bytes_feature(value):\n  if isinstance(value, type(tf.constant(0))):\n    value = value.numpy() # BytesList won't unpack a string from an EagerTensor.\n  return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))\n\ndef _int64_feature(value):\n  return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))\n\ndef serialize_example(image, x1, y1):\n  feature = {\n      'image': _bytes_feature(image),\n      'x1': _int64_feature(x1),\n      'y1': _int64_feature(y1)\n  }\n  example_proto = tf.train.Example(features=tf.train.Features(feature=feature))\n  return example_proto.SerializeToString()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"p = pathlib.Path('../input/hubmap-kidney-segmentation')\nidentity = rasterio.Affine(1, 0, 0, 0, 1, 0)\nos.makedirs('test', exist_ok = True)\n\nfor i, filename in tqdm(enumerate(p.glob('test/*.tiff')), \n                        total = len(list(p.glob('test/*.tiff')))):\n    \n    print(f'{i+1} Creating tfrecords for image: {filename.stem}')\n    dataset = rasterio.open(filename.as_posix(), transform = identity)\n    slices = make_grid(dataset.shape, window=WINDOW, min_overlap=MIN_OVERLAP)\n    \n    print(slices.shape[0])\n    cnt = 0\n    part = 0 \n    fname = f'test/{filename.stem}-part{part}.tfrec'\n    writer = tf.io.TFRecordWriter(fname) \n    for (x1,x2,y1,y2) in slices:\n        if cnt>999:\n            writer.close()\n            os.rename(fname, f'test/{filename.stem}-part{part}-{cnt}.tfrec')\n            part += 1\n            fname = f'test/{filename.stem}-part{part}.tfrec'\n            writer = tf.io.TFRecordWriter(fname)\n            cnt = 0\n        \n        image = dataset.read([1,2,3],\n                    window=Window.from_slices((x1,x2),(y1,y2)))\n        image = np.moveaxis(image, 0, -1)\n        image = cv2.resize(image, (NEW_SIZE, NEW_SIZE),interpolation = cv2.INTER_AREA)\n        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)\n        example = serialize_example(image.tobytes(),x1,y1)\n        writer.write(example)\n        cnt+=1\n    writer.close()\n    del writer\n    os.rename(fname, f'test/{filename.stem}-part{part}-{cnt}.tfrec')\n    gc.collect();","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images = glob.glob('test/*.tfrec')\nctesti = count_data_items(test_images)\nprint(f'Num test images: {ctesti}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"DIM = sz\nmini_size = 64\ndef _parse_image_function(example_proto):\n    image_feature_description = {\n        'image': tf.io.FixedLenFeature([], tf.string),\n        'x1': tf.io.FixedLenFeature([], tf.int64),\n        'y1': tf.io.FixedLenFeature([], tf.int64)\n    }\n    single_example = tf.io.parse_single_example(example_proto, image_feature_description)\n    image = tf.reshape( tf.io.decode_raw(single_example['image'],out_type=np.dtype('uint8')), (DIM,DIM, 3))\n    x1 = single_example['x1']\n    y1 = single_example['y1']\n    image = tf.image.resize(image,(mini_size,mini_size))/255.0\n    return image, x1, y1\n\n\ndef load_dataset(filenames):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(lambda ex: _parse_image_function(ex))\n    return dataset\n\nN = 8\ndef get_dataset(FILENAME):\n    dataset = load_dataset(FILENAME)\n    dataset = dataset.batch(N*N)\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for imgs, x1, y1 in get_dataset(test_images[0]).take(1):\n    pass\n\nplt.figure(figsize = (N,N))\ngs1 = gridspec.GridSpec(N,N)\n\nfor i in range(N*N):\n   # i = i + 1 # grid spec indexes from 0\n    ax1 = plt.subplot(gs1[i])\n    plt.axis('on')\n    ax1.set_xticklabels([])\n    ax1.set_yticklabels([])\n    ax1.set_aspect('equal')\n    ax1.set_title(f'{x1[i]}; {y1[i]}', fontsize=6)\n    ax1.imshow(imgs[i])\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}