99 KiB
99 KiB
Mask R-CNN - Train on Shapes Dataset¶
This notebook shows how to train Mask R-CNN on your own dataset. To keep things simple we use a synthetic dataset of shapes (squares, triangles, and circles) which enables fast training. You'd still need a GPU, though, because the network backbone is a Resnet101, which would be too slow to train on a CPU. On a GPU, you can start to get okay-ish results in a few minutes, and good results in less than an hour.
The code of the Shapes dataset is included below. It generates images on the fly, so it doesn't require downloading any data. And it can generate images of any size, so we pick a small image size to train faster.
In [1]:
import os import sys import random import math import re import time import numpy as np import cv2 import matplotlib import matplotlib.pyplot as plt # Root directory of the project ROOT_DIR = os.path.abspath("../../") # Import Mask RCNN sys.path.append(ROOT_DIR) # To find local version of the library from mrcnn.config import Config from mrcnn import utils import mrcnn.model as modellib from mrcnn import visualize from mrcnn.model import log %matplotlib inline # Directory to save logs and trained model MODEL_DIR = os.path.join(ROOT_DIR, "logs") # Local path to trained weights file COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5") # Download COCO trained weights from Releases if needed if not os.path.exists(COCO_MODEL_PATH): utils.download_trained_weights(COCO_MODEL_PATH)
Using TensorFlow backend.
Configurations¶
In [2]:
class ShapesConfig(Config): """Configuration for training on the toy shapes dataset. Derives from the base Config class and overrides values specific to the toy shapes dataset. """ # Give the configuration a recognizable name NAME = "shapes" # Train on 1 GPU and 8 images per GPU. We can put multiple images on each # GPU because the images are small. Batch size is 8 (GPUs * images/GPU). GPU_COUNT = 1 IMAGES_PER_GPU = 8 # Number of classes (including background) NUM_CLASSES = 1 + 3 # background + 3 shapes # Use small images for faster training. Set the limits of the small side # the large side, and that determines the image shape. IMAGE_MIN_DIM = 128 IMAGE_MAX_DIM = 128 # Use smaller anchors because our image and objects are small RPN_ANCHOR_SCALES = (8, 16, 32, 64, 128) # anchor side in pixels # Reduce training ROIs per image because the images are small and have # few objects. Aim to allow ROI sampling to pick 33% positive ROIs. TRAIN_ROIS_PER_IMAGE = 32 # Use a small epoch since the data is simple STEPS_PER_EPOCH = 100 # use small validation steps since the epoch is small VALIDATION_STEPS = 5 config = ShapesConfig() config.display()
Configurations: BACKBONE_SHAPES [[32 32] [16 16] [ 8 8] [ 4 4] [ 2 2]] BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 8 BBOX_STD_DEV [ 0.1 0.1 0.2 0.2] DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.5 DETECTION_NMS_THRESHOLD 0.3 GPU_COUNT 1 IMAGES_PER_GPU 8 IMAGE_MAX_DIM 128 IMAGE_MIN_DIM 128 IMAGE_PADDING True IMAGE_SHAPE [128 128 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.002 MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [ 123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME SHAPES NUM_CLASSES 4 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (8, 16, 32, 64, 128) RPN_ANCHOR_STRIDE 2 RPN_BBOX_STD_DEV [ 0.1 0.1 0.2 0.2] RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 100 TRAIN_ROIS_PER_IMAGE 32 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001
Notebook Preferences¶
In [3]:
def get_ax(rows=1, cols=1, size=8): """Return a Matplotlib Axes array to be used in all visualizations in the notebook. Provide a central point to control graph sizes. Change the default size attribute to control the size of rendered images """ _, ax = plt.subplots(rows, cols, figsize=(size*cols, size*rows)) return ax
Dataset¶
Create a synthetic dataset
Extend the Dataset class and add a method to load the shapes dataset, load_shapes(), and override the following methods:
- load_image()
- load_mask()
- image_reference()
In [4]:
class ShapesDataset(utils.Dataset): """Generates the shapes synthetic dataset. The dataset consists of simple shapes (triangles, squares, circles) placed randomly on a blank surface. The images are generated on the fly. No file access required. """ def load_shapes(self, count, height, width): """Generate the requested number of synthetic images. count: number of images to generate. height, width: the size of the generated images. """ # Add classes self.add_class("shapes", 1, "square") self.add_class("shapes", 2, "circle") self.add_class("shapes", 3, "triangle") # Add images # Generate random specifications of images (i.e. color and # list of shapes sizes and locations). This is more compact than # actual images. Images are generated on the fly in load_image(). for i in range(count): bg_color, shapes = self.random_image(height, width) self.add_image("shapes", image_id=i, path=None, width=width, height=height, bg_color=bg_color, shapes=shapes) def load_image(self, image_id): """Generate an image from the specs of the given image ID. Typically this function loads the image from a file, but in this case it generates the image on the fly from the specs in image_info. """ info = self.image_info[image_id] bg_color = np.array(info['bg_color']).reshape([1, 1, 3]) image = np.ones([info['height'], info['width'], 3], dtype=np.uint8) image = image * bg_color.astype(np.uint8) for shape, color, dims in info['shapes']: image = self.draw_shape(image, shape, dims, color) return image def image_reference(self, image_id): """Return the shapes data of the image.""" info = self.image_info[image_id] if info["source"] == "shapes": return info["shapes"] else: super(self.__class__).image_reference(self, image_id) def load_mask(self, image_id): """Generate instance masks for shapes of the given image ID. """ info = self.image_info[image_id] shapes = info['shapes'] count = len(shapes) mask = np.zeros([info['height'], info['width'], count], dtype=np.uint8) for i, (shape, _, dims) in enumerate(info['shapes']): mask[:, :, i:i+1] = self.draw_shape(mask[:, :, i:i+1].copy(), shape, dims, 1) # Handle occlusions occlusion = np.logical_not(mask[:, :, -1]).astype(np.uint8) for i in range(count-2, -1, -1): mask[:, :, i] = mask[:, :, i] * occlusion occlusion = np.logical_and(occlusion, np.logical_not(mask[:, :, i])) # Map class names to class IDs. class_ids = np.array([self.class_names.index(s[0]) for s in shapes]) return mask.astype(np.bool), class_ids.astype(np.int32) def draw_shape(self, image, shape, dims, color): """Draws a shape from the given specs.""" # Get the center x, y and the size s x, y, s = dims if shape == 'square': cv2.rectangle(image, (x-s, y-s), (x+s, y+s), color, -1) elif shape == "circle": cv2.circle(image, (x, y), s, color, -1) elif shape == "triangle": points = np.array([[(x, y-s), (x-s/math.sin(math.radians(60)), y+s), (x+s/math.sin(math.radians(60)), y+s), ]], dtype=np.int32) cv2.fillPoly(image, points, color) return image def random_shape(self, height, width): """Generates specifications of a random shape that lies within the given height and width boundaries. Returns a tuple of three valus: * The shape name (square, circle, ...) * Shape color: a tuple of 3 values, RGB. * Shape dimensions: A tuple of values that define the shape size and location. Differs per shape type. """ # Shape shape = random.choice(["square", "circle", "triangle"]) # Color color = tuple([random.randint(0, 255) for _ in range(3)]) # Center x, y buffer = 20 y = random.randint(buffer, height - buffer - 1) x = random.randint(buffer, width - buffer - 1) # Size s = random.randint(buffer, height//4) return shape, color, (x, y, s) def random_image(self, height, width): """Creates random specifications of an image with multiple shapes. Returns the background color of the image and a list of shape specifications that can be used to draw the image. """ # Pick random background color bg_color = np.array([random.randint(0, 255) for _ in range(3)]) # Generate a few random shapes and record their # bounding boxes shapes = [] boxes = [] N = random.randint(1, 4) for _ in range(N): shape, color, dims = self.random_shape(height, width) shapes.append((shape, color, dims)) x, y, s = dims boxes.append([y-s, x-s, y+s, x+s]) # Apply non-max suppression wit 0.3 threshold to avoid # shapes covering each other keep_ixs = utils.non_max_suppression(np.array(boxes), np.arange(N), 0.3) shapes = [s for i, s in enumerate(shapes) if i in keep_ixs] return bg_color, shapes
In [5]:
# Training dataset dataset_train = ShapesDataset() dataset_train.load_shapes(500, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1]) dataset_train.prepare() # Validation dataset dataset_val = ShapesDataset() dataset_val.load_shapes(50, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1]) dataset_val.prepare()
In [6]:
# Load and display random samples image_ids = np.random.choice(dataset_train.image_ids, 4) for image_id in image_ids: image = dataset_train.load_image(image_id) mask, class_ids = dataset_train.load_mask(image_id) visualize.display_top_masks(image, mask, class_ids, dataset_train.class_names)
Create Model¶
In [ ]:
# Create model in training mode model = modellib.MaskRCNN(mode="training", config=config, model_dir=MODEL_DIR)
In [7]:
# Which weights to start with? init_with = "coco" # imagenet, coco, or last if init_with == "imagenet": model.load_weights(model.get_imagenet_weights(), by_name=True) elif init_with == "coco": # Load weights trained on MS COCO, but skip layers that # are different due to the different number of classes # See README for instructions to download the COCO weights model.load_weights(COCO_MODEL_PATH, by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox", "mrcnn_mask"]) elif init_with == "last": # Load the last model you trained and continue training model.load_weights(model.find_last(), by_name=True)
Training¶
Train in two stages:
Only the heads. Here we're freezing all the backbone layers and training only the randomly initialized layers (i.e. the ones that we didn't use pre-trained weights from MS COCO). To train only the head layers, pass
layers='heads'to thetrain()function.Fine-tune all layers. For this simple example it's not necessary, but we're including it to show the process. Simply pass
layers="allto train all layers.
In [8]:
# Train the head branches # Passing layers="heads" freezes all layers except the head # layers. You can also pass a regular expression to select # which layers to train by name pattern. model.train(dataset_train, dataset_val, learning_rate=config.LEARNING_RATE, epochs=1, layers='heads')
Checkpoint Path: /deepmatter/mask_rcnn/logs/shapes2017102802/mask_rcnn_{epoch:04d}.h5
Starting at epoch 0. LR=0.002
Selecting layers to train
fpn_c5p5 (Conv2D)
fpn_c4p4 (Conv2D)
fpn_c3p3 (Conv2D)
fpn_c2p2 (Conv2D)
fpn_p5 (Conv2D)
fpn_p2 (Conv2D)
fpn_p3 (Conv2D)
fpn_p4 (Conv2D)
In model: rpn_model
rpn_conv_shared (Conv2D)
rpn_class_raw (Conv2D)
rpn_bbox_pred (Conv2D)
mrcnn_mask_conv1 (TimeDistributed)
mrcnn_mask_bn1 (TimeDistributed)
mrcnn_mask_conv2 (TimeDistributed)
mrcnn_mask_bn2 (TimeDistributed)
mrcnn_class_conv1 (TimeDistributed)
mrcnn_class_bn1 (TimeDistributed)
mrcnn_mask_conv3 (TimeDistributed)
mrcnn_mask_bn3 (TimeDistributed)
mrcnn_class_conv2 (TimeDistributed)
mrcnn_class_bn2 (TimeDistributed)
mrcnn_mask_conv4 (TimeDistributed)
mrcnn_mask_bn4 (TimeDistributed)
mrcnn_bbox_fc (TimeDistributed)
mrcnn_mask_deconv (TimeDistributed)
mrcnn_class_logits (TimeDistributed)
mrcnn_mask (TimeDistributed)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gradients_impl.py:95: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
/usr/local/lib/python3.5/dist-packages/keras/engine/training.py:1987: UserWarning: Using a generator with `use_multiprocessing=True` and multiple workers may duplicate your data. Please consider using the`keras.utils.Sequence class.
UserWarning('Using a generator with `use_multiprocessing=True`'
Epoch 1/1 100/100 [==============================] - 73s - loss: 2.2164 - rpn_class_loss: 0.0242 - rpn_bbox_loss: 1.0638 - mrcnn_class_loss: 0.2426 - mrcnn_bbox_loss: 0.3006 - mrcnn_mask_loss: 0.2385 - val_loss: 1.8454 - val_rpn_class_loss: 0.0232 - val_rpn_bbox_loss: 0.9971 - val_mrcnn_class_loss: 0.1398 - val_mrcnn_bbox_loss: 0.1343 - val_mrcnn_mask_loss: 0.2042
In [9]:
# Fine tune all layers # Passing layers="all" trains all layers. You can also # pass a regular expression to select which layers to # train by name pattern. model.train(dataset_train, dataset_val, learning_rate=config.LEARNING_RATE / 10, epochs=2, layers="all")
Checkpoint Path: /deepmatter/mask_rcnn/logs/shapes2017102802/mask_rcnn_{epoch:04d}.h5
Starting at epoch 0. LR=0.0002
Selecting layers to train
conv1 (Conv2D)
bn_conv1 (BatchNorm)
res2a_branch2a (Conv2D)
bn2a_branch2a (BatchNorm)
res2a_branch2b (Conv2D)
bn2a_branch2b (BatchNorm)
res2a_branch2c (Conv2D)
res2a_branch1 (Conv2D)
bn2a_branch2c (BatchNorm)
bn2a_branch1 (BatchNorm)
res2b_branch2a (Conv2D)
bn2b_branch2a (BatchNorm)
res2b_branch2b (Conv2D)
bn2b_branch2b (BatchNorm)
res2b_branch2c (Conv2D)
bn2b_branch2c (BatchNorm)
res2c_branch2a (Conv2D)
bn2c_branch2a (BatchNorm)
res2c_branch2b (Conv2D)
bn2c_branch2b (BatchNorm)
res2c_branch2c (Conv2D)
bn2c_branch2c (BatchNorm)
res3a_branch2a (Conv2D)
bn3a_branch2a (BatchNorm)
res3a_branch2b (Conv2D)
bn3a_branch2b (BatchNorm)
res3a_branch2c (Conv2D)
res3a_branch1 (Conv2D)
bn3a_branch2c (BatchNorm)
bn3a_branch1 (BatchNorm)
res3b_branch2a (Conv2D)
bn3b_branch2a (BatchNorm)
res3b_branch2b (Conv2D)
bn3b_branch2b (BatchNorm)
res3b_branch2c (Conv2D)
bn3b_branch2c (BatchNorm)
res3c_branch2a (Conv2D)
bn3c_branch2a (BatchNorm)
res3c_branch2b (Conv2D)
bn3c_branch2b (BatchNorm)
res3c_branch2c (Conv2D)
bn3c_branch2c (BatchNorm)
res3d_branch2a (Conv2D)
bn3d_branch2a (BatchNorm)
res3d_branch2b (Conv2D)
bn3d_branch2b (BatchNorm)
res3d_branch2c (Conv2D)
bn3d_branch2c (BatchNorm)
res4a_branch2a (Conv2D)
bn4a_branch2a (BatchNorm)
res4a_branch2b (Conv2D)
bn4a_branch2b (BatchNorm)
res4a_branch2c (Conv2D)
res4a_branch1 (Conv2D)
bn4a_branch2c (BatchNorm)
bn4a_branch1 (BatchNorm)
res4b_branch2a (Conv2D)
bn4b_branch2a (BatchNorm)
res4b_branch2b (Conv2D)
bn4b_branch2b (BatchNorm)
res4b_branch2c (Conv2D)
bn4b_branch2c (BatchNorm)
res4c_branch2a (Conv2D)
bn4c_branch2a (BatchNorm)
res4c_branch2b (Conv2D)
bn4c_branch2b (BatchNorm)
res4c_branch2c (Conv2D)
bn4c_branch2c (BatchNorm)
res4d_branch2a (Conv2D)
bn4d_branch2a (BatchNorm)
res4d_branch2b (Conv2D)
bn4d_branch2b (BatchNorm)
res4d_branch2c (Conv2D)
bn4d_branch2c (BatchNorm)
res4e_branch2a (Conv2D)
bn4e_branch2a (BatchNorm)
res4e_branch2b (Conv2D)
bn4e_branch2b (BatchNorm)
res4e_branch2c (Conv2D)
bn4e_branch2c (BatchNorm)
res4f_branch2a (Conv2D)
bn4f_branch2a (BatchNorm)
res4f_branch2b (Conv2D)
bn4f_branch2b (BatchNorm)
res4f_branch2c (Conv2D)
bn4f_branch2c (BatchNorm)
res4g_branch2a (Conv2D)
bn4g_branch2a (BatchNorm)
res4g_branch2b (Conv2D)
bn4g_branch2b (BatchNorm)
res4g_branch2c (Conv2D)
bn4g_branch2c (BatchNorm)
res4h_branch2a (Conv2D)
bn4h_branch2a (BatchNorm)
res4h_branch2b (Conv2D)
bn4h_branch2b (BatchNorm)
res4h_branch2c (Conv2D)
bn4h_branch2c (BatchNorm)
res4i_branch2a (Conv2D)
bn4i_branch2a (BatchNorm)
res4i_branch2b (Conv2D)
bn4i_branch2b (BatchNorm)
res4i_branch2c (Conv2D)
bn4i_branch2c (BatchNorm)
res4j_branch2a (Conv2D)
bn4j_branch2a (BatchNorm)
res4j_branch2b (Conv2D)
bn4j_branch2b (BatchNorm)
res4j_branch2c (Conv2D)
bn4j_branch2c (BatchNorm)
res4k_branch2a (Conv2D)
bn4k_branch2a (BatchNorm)
res4k_branch2b (Conv2D)
bn4k_branch2b (BatchNorm)
res4k_branch2c (Conv2D)
bn4k_branch2c (BatchNorm)
res4l_branch2a (Conv2D)
bn4l_branch2a (BatchNorm)
res4l_branch2b (Conv2D)
bn4l_branch2b (BatchNorm)
res4l_branch2c (Conv2D)
bn4l_branch2c (BatchNorm)
res4m_branch2a (Conv2D)
bn4m_branch2a (BatchNorm)
res4m_branch2b (Conv2D)
bn4m_branch2b (BatchNorm)
res4m_branch2c (Conv2D)
bn4m_branch2c (BatchNorm)
res4n_branch2a (Conv2D)
bn4n_branch2a (BatchNorm)
res4n_branch2b (Conv2D)
bn4n_branch2b (BatchNorm)
res4n_branch2c (Conv2D)
bn4n_branch2c (BatchNorm)
res4o_branch2a (Conv2D)
bn4o_branch2a (BatchNorm)
res4o_branch2b (Conv2D)
bn4o_branch2b (BatchNorm)
res4o_branch2c (Conv2D)
bn4o_branch2c (BatchNorm)
res4p_branch2a (Conv2D)
bn4p_branch2a (BatchNorm)
res4p_branch2b (Conv2D)
bn4p_branch2b (BatchNorm)
res4p_branch2c (Conv2D)
bn4p_branch2c (BatchNorm)
res4q_branch2a (Conv2D)
bn4q_branch2a (BatchNorm)
res4q_branch2b (Conv2D)
bn4q_branch2b (BatchNorm)
res4q_branch2c (Conv2D)
bn4q_branch2c (BatchNorm)
res4r_branch2a (Conv2D)
bn4r_branch2a (BatchNorm)
res4r_branch2b (Conv2D)
bn4r_branch2b (BatchNorm)
res4r_branch2c (Conv2D)
bn4r_branch2c (BatchNorm)
res4s_branch2a (Conv2D)
bn4s_branch2a (BatchNorm)
res4s_branch2b (Conv2D)
bn4s_branch2b (BatchNorm)
res4s_branch2c (Conv2D)
bn4s_branch2c (BatchNorm)
res4t_branch2a (Conv2D)
bn4t_branch2a (BatchNorm)
res4t_branch2b (Conv2D)
bn4t_branch2b (BatchNorm)
res4t_branch2c (Conv2D)
bn4t_branch2c (BatchNorm)
res4u_branch2a (Conv2D)
bn4u_branch2a (BatchNorm)
res4u_branch2b (Conv2D)
bn4u_branch2b (BatchNorm)
res4u_branch2c (Conv2D)
bn4u_branch2c (BatchNorm)
res4v_branch2a (Conv2D)
bn4v_branch2a (BatchNorm)
res4v_branch2b (Conv2D)
bn4v_branch2b (BatchNorm)
res4v_branch2c (Conv2D)
bn4v_branch2c (BatchNorm)
res4w_branch2a (Conv2D)
bn4w_branch2a (BatchNorm)
res4w_branch2b (Conv2D)
bn4w_branch2b (BatchNorm)
res4w_branch2c (Conv2D)
bn4w_branch2c (BatchNorm)
res5a_branch2a (Conv2D)
bn5a_branch2a (BatchNorm)
res5a_branch2b (Conv2D)
bn5a_branch2b (BatchNorm)
res5a_branch2c (Conv2D)
res5a_branch1 (Conv2D)
bn5a_branch2c (BatchNorm)
bn5a_branch1 (BatchNorm)
res5b_branch2a (Conv2D)
bn5b_branch2a (BatchNorm)
res5b_branch2b (Conv2D)
bn5b_branch2b (BatchNorm)
res5b_branch2c (Conv2D)
bn5b_branch2c (BatchNorm)
res5c_branch2a (Conv2D)
bn5c_branch2a (BatchNorm)
res5c_branch2b (Conv2D)
bn5c_branch2b (BatchNorm)
res5c_branch2c (Conv2D)
bn5c_branch2c (BatchNorm)
fpn_c5p5 (Conv2D)
fpn_c4p4 (Conv2D)
fpn_c3p3 (Conv2D)
fpn_c2p2 (Conv2D)
fpn_p5 (Conv2D)
fpn_p2 (Conv2D)
fpn_p3 (Conv2D)
fpn_p4 (Conv2D)
In model: rpn_model
rpn_conv_shared (Conv2D)
rpn_class_raw (Conv2D)
rpn_bbox_pred (Conv2D)
mrcnn_mask_conv1 (TimeDistributed)
mrcnn_mask_bn1 (TimeDistributed)
mrcnn_mask_conv2 (TimeDistributed)
mrcnn_mask_bn2 (TimeDistributed)
mrcnn_class_conv1 (TimeDistributed)
mrcnn_class_bn1 (TimeDistributed)
mrcnn_mask_conv3 (TimeDistributed)
mrcnn_mask_bn3 (TimeDistributed)
mrcnn_class_conv2 (TimeDistributed)
mrcnn_class_bn2 (TimeDistributed)
mrcnn_mask_conv4 (TimeDistributed)
mrcnn_mask_bn4 (TimeDistributed)
mrcnn_bbox_fc (TimeDistributed)
mrcnn_mask_deconv (TimeDistributed)
mrcnn_class_logits (TimeDistributed)
mrcnn_mask (TimeDistributed)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gradients_impl.py:95: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
/usr/local/lib/python3.5/dist-packages/keras/engine/training.py:1987: UserWarning: Using a generator with `use_multiprocessing=True` and multiple workers may duplicate your data. Please consider using the`keras.utils.Sequence class.
UserWarning('Using a generator with `use_multiprocessing=True`'
Epoch 1/1 100/100 [==============================] - 86s - loss: 11.4006 - rpn_class_loss: 0.0184 - rpn_bbox_loss: 0.8409 - mrcnn_class_loss: 0.1576 - mrcnn_bbox_loss: 0.0902 - mrcnn_mask_loss: 0.1977 - val_loss: 11.4376 - val_rpn_class_loss: 0.0220 - val_rpn_bbox_loss: 1.0068 - val_mrcnn_class_loss: 0.1172 - val_mrcnn_bbox_loss: 0.0683 - val_mrcnn_mask_loss: 0.1278
In [10]:
# Save weights # Typically not needed because callbacks save after every epoch # Uncomment to save manually # model_path = os.path.join(MODEL_DIR, "mask_rcnn_shapes.h5") # model.keras_model.save_weights(model_path)
Detection¶
In [11]:
class InferenceConfig(ShapesConfig): GPU_COUNT = 1 IMAGES_PER_GPU = 1 inference_config = InferenceConfig() # Recreate the model in inference mode model = modellib.MaskRCNN(mode="inference", config=inference_config, model_dir=MODEL_DIR) # Get path to saved weights # Either set a specific path or find last trained weights # model_path = os.path.join(ROOT_DIR, ".h5 file name here") model_path = model.find_last() # Load trained weights print("Loading weights from ", model_path) model.load_weights(model_path, by_name=True)
In [12]:
# Test on a random image image_id = random.choice(dataset_val.image_ids) original_image, image_meta, gt_class_id, gt_bbox, gt_mask =\ modellib.load_image_gt(dataset_val, inference_config, image_id, use_mini_mask=False) log("original_image", original_image) log("image_meta", image_meta) log("gt_class_id", gt_class_id) log("gt_bbox", gt_bbox) log("gt_mask", gt_mask) visualize.display_instances(original_image, gt_bbox, gt_mask, gt_class_id, dataset_train.class_names, figsize=(8, 8))
original_image shape: (128, 128, 3) min: 108.00000 max: 236.00000 image_meta shape: (12,) min: 0.00000 max: 128.00000 gt_bbox shape: (2, 5) min: 2.00000 max: 102.00000 gt_mask shape: (128, 128, 2) min: 0.00000 max: 1.00000
In [13]:
results = model.detect([original_image], verbose=1) r = results[0] visualize.display_instances(original_image, r['rois'], r['masks'], r['class_ids'], dataset_val.class_names, r['scores'], ax=get_ax())
Processing 1 images image shape: (128, 128, 3) min: 108.00000 max: 236.00000 molded_images shape: (1, 128, 128, 3) min: -15.70000 max: 132.10000 image_metas shape: (1, 12) min: 0.00000 max: 128.00000
Evaluation¶
In [14]:
# Compute VOC-Style mAP @ IoU=0.5 # Running on 10 images. Increase for better accuracy. image_ids = np.random.choice(dataset_val.image_ids, 10) APs = [] for image_id in image_ids: # Load image and ground truth data image, image_meta, gt_class_id, gt_bbox, gt_mask =\ modellib.load_image_gt(dataset_val, inference_config, image_id, use_mini_mask=False) molded_images = np.expand_dims(modellib.mold_image(image, inference_config), 0) # Run object detection results = model.detect([image], verbose=0) r = results[0] # Compute AP AP, precisions, recalls, overlaps =\ utils.compute_ap(gt_bbox, gt_class_id, gt_mask, r["rois"], r["class_ids"], r["scores"], r['masks']) APs.append(AP) print("mAP: ", np.mean(APs))
mAP: 0.95
In [ ]: