I am a newbie to deep learning so while I am trying to build a Masked R-CNN model for training my Custom Dataset I am getting an error which reads:
TypeError: Could not build a TypeSpec for <KerasTensor: shape=(None, None, 4) dtype=float32 (created by layer 'tf.math.truediv')> with type KerasTensor
Below is the PYTHON CODE I am trying to implement for building my ** Masked R-CNN model**:
Mask R-CNN
Configurations and data loading code for MS COCO.
Copyright (c) 2017 Matterport, Inc.
Licensed under the MIT License (see LICENSE for details)
Written by Waleed Abdulla
------------------------------------------------------------
Usage: import the module (see Jupyter notebooks for examples), or run from
the command line as such:
# Train a new model starting from pre-trained COCO weights
python3 coco.py train --dataset=/path/to/coco/ --model=coco
# Train a new model starting from ImageNet weights. Also auto download COCO dataset
python3 coco.py train --dataset=/path/to/coco/ --model=imagenet --download=True
# Continue training a model that you had trained earlier
python3 coco.py train --dataset=/path/to/coco/ --model=/path/to/weights.h5
# Continue training the last model you trained
python3 coco.py train --dataset=/path/to/coco/ --model=last
# Run COCO evaluatoin on the last model you trained
python3 coco.py evaluate --dataset=/path/to/coco/ --model=last
"""
import os
import sys
import time
import numpy as np
import imgaug # https://github.com/aleju/imgaug (pip3 install imgaug)
# Download and install the Python COCO tools from https://github.com/waleedka/coco
# That's a fork from the original https://github.com/pdollar/coco with a bug
# fix for Python 3.
# I submitted a pull request https://github.com/cocodataset/cocoapi/pull/50
# If the PR is merged then use the original repo.
# Note: Edit PythonAPI/Makefile and replace "python" with "python3".
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
from pycocotools import mask as maskUtils
import zipfile
import urllib.request
import shutil
# 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 model as modellib, utils
# Path to trained weights file
COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")
# Directory to save logs and model checkpoints, if not provided
# through the command line argument --logs
DEFAULT_LOGS_DIR = os.path.join(ROOT_DIR, "Mask_RCNN\\logs")
DEFAULT_DATASET_YEAR = "2014"
############################################################
# Configurations
############################################################
class CocoConfig(Config):
"""Configuration for training on MS COCO.
Derives from the base Config class and overrides values specific
to the COCO dataset.
"""
# Give the configuration a recognizable name
NAME = "coco"
# We use a GPU with 12GB memory, which can fit two images.
# Adjust down if you use a smaller GPU.
IMAGES_PER_GPU = 2
# Uncomment to train on 8 GPUs (default is 1)
# GPU_COUNT = 8
# Number of classes (including background)
NUM_CLASSES = 1 + 80 # COCO has 80 classes
############################################################
# Dataset
############################################################
class CocoDataset(utils.Dataset):
def load_coco(self, dataset_dir, subset, year=DEFAULT_DATASET_YEAR, class_ids=None,
class_map=None, return_coco=False, auto_download=False):
"""Load a subset of the COCO dataset.
dataset_dir: The root directory of the COCO dataset.
subset: What to load (train, val, minival, valminusminival)
year: What dataset year to load (2014, 2017) as a string, not an integer
class_ids: If provided, only loads images that have the given classes.
class_map: TODO: Not implemented yet. Supports maping classes from
different datasets to the same class ID.
return_coco: If True, returns the COCO object.
auto_download: Automatically download and unzip MS-COCO images and annotations
"""
if auto_download is True:
self.auto_download(dataset_dir, subset, year)
coco = COCO("{}/annotations/instances_{}{}.json".format(dataset_dir, subset, year))
if subset == "minival" or subset == "valminusminival":
subset = "val"
image_dir = "{}/{}{}".format(dataset_dir, subset, year)
# Load all classes or a subset?
if not class_ids:
# All classes
class_ids = sorted(coco.getCatIds())
# All images or a subset?
if class_ids:
image_ids = []
for id in class_ids:
image_ids.extend(list(coco.getImgIds(catIds=[id])))
# Remove duplicates
image_ids = list(set(image_ids))
else:
# All images
image_ids = list(coco.imgs.keys())
# Add classes
for i in class_ids:
self.add_class("coco", i, coco.loadCats(i)[0]["name"])
# Add images
for i in image_ids:
self.add_image(
"coco", image_id=i,
path=os.path.join(image_dir, coco.imgs[i]['file_name']),
width=coco.imgs[i]["width"],
height=coco.imgs[i]["height"],
annotations=coco.loadAnns(coco.getAnnIds(
imgIds=[i], catIds=class_ids, iscrowd=None)))
if return_coco:
return coco
def auto_download(self, dataDir, dataType, dataYear):
"""Download the COCO dataset/annotations if requested.
dataDir: The root directory of the COCO dataset.
dataType: What to load (train, val, minival, valminusminival)
dataYear: What dataset year to load (2014, 2017) as a string, not an integer
Note:
For 2014, use "train", "val", "minival", or "valminusminival"
For 2017, only "train" and "val" annotations are available
"""
# Setup paths and file names
if dataType == "minival" or dataType == "valminusminival":
imgDir = "{}/{}{}".format(dataDir, "val", dataYear)
imgZipFile = "{}/{}{}.zip".format(dataDir, "val", dataYear)
imgURL = "http://images.cocodataset.org/zips/{}{}.zip".format("val", dataYear)
else:
imgDir = "{}/{}{}".format(dataDir, dataType, dataYear)
imgZipFile = "{}/{}{}.zip".format(dataDir, dataType, dataYear)
imgURL = "http://images.cocodataset.org/zips/{}{}.zip".format(dataType, dataYear)
# print("Image paths:"); print(imgDir); print(imgZipFile); print(imgURL)
# Create main folder if it doesn't exist yet
if not os.path.exists(dataDir):
os.makedirs(dataDir)
# Download images if not available locally
if not os.path.exists(imgDir):
os.makedirs(imgDir)
print("Downloading images to " + imgZipFile + " ...")
with urllib.request.urlopen(imgURL) as resp, open(imgZipFile, 'wb') as out:
shutil.copyfileobj(resp, out)
print("... done downloading.")
print("Unzipping " + imgZipFile)
with zipfile.ZipFile(imgZipFile, "r") as zip_ref:
zip_ref.extractall(dataDir)
print("... done unzipping")
print("Will use images in " + imgDir)
# Setup annotations data paths
annDir = "{}/annotations".format(dataDir)
if dataType == "minival":
annZipFile = "{}/instances_minival2014.json.zip".format(dataDir)
annFile = "{}/instances_minival2014.json".format(annDir)
annURL = "https://dl.dropboxusercontent.com/s/o43o90bna78omob/instances_minival2014.json.zip?dl=0"
unZipDir = annDir
elif dataType == "valminusminival":
annZipFile = "{}/instances_valminusminival2014.json.zip".format(dataDir)
annFile = "{}/instances_valminusminival2014.json".format(annDir)
annURL = "https://dl.dropboxusercontent.com/s/s3tw5zcg7395368/instances_valminusminival2014.json.zip?dl=0"
unZipDir = annDir
else:
annZipFile = "{}/annotations_trainval{}.zip".format(dataDir, dataYear)
annFile = "{}/instances_{}{}.json".format(annDir, dataType, dataYear)
annURL = "http://images.cocodataset.org/annotations/annotations_trainval{}.zip".format(dataYear)
unZipDir = dataDir
# print("Annotations paths:"); print(annDir); print(annFile); print(annZipFile); print(annURL)
# Download annotations if not available locally
if not os.path.exists(annDir):
os.makedirs(annDir)
if not os.path.exists(annFile):
if not os.path.exists(annZipFile):
print("Downloading zipped annotations to " + annZipFile + " ...")
with urllib.request.urlopen(annURL) as resp, open(annZipFile, 'wb') as out:
shutil.copyfileobj(resp, out)
print("... done downloading.")
print("Unzipping " + annZipFile)
with zipfile.ZipFile(annZipFile, "r") as zip_ref:
zip_ref.extractall(unZipDir)
print("... done unzipping")
print("Will use annotations in " + annFile)
def load_mask(self, image_id):
"""Load instance masks for the given image.
Different datasets use different ways to store masks. This
function converts the different mask format to one format
in the form of a bitmap [height, width, instances].
Returns:
masks: A bool array of shape [height, width, instance count] with
one mask per instance.
class_ids: a 1D array of class IDs of the instance masks.
"""
# If not a COCO image, delegate to parent class.
image_info = self.image_info[image_id]
if image_info["source"] != "coco":
return super(CocoDataset, self).load_mask(image_id)
instance_masks = []
class_ids = []
annotations = self.image_info[image_id]["annotations"]
# Build mask of shape [height, width, instance_count] and list
# of class IDs that correspond to each channel of the mask.
for annotation in annotations:
class_id = self.map_source_class_id(
"coco.{}".format(annotation['category_id']))
if class_id:
m = self.annToMask(annotation, image_info["height"],
image_info["width"])
# Some objects are so small that they're less than 1 pixel area
# and end up rounded out. Skip those objects.
if m.max() < 1:
continue
# Is it a crowd? If so, use a negative class ID.
if annotation['iscrowd']:
# Use negative class ID for crowds
class_id *= -1
# For crowd masks, annToMask() sometimes returns a mask
# smaller than the given dimensions. If so, resize it.
if m.shape[0] != image_info["height"] or m.shape[1] != image_info["width"]:
m = np.ones([image_info["height"], image_info["width"]], dtype=bool)
instance_masks.append(m)
class_ids.append(class_id)
# Pack instance masks into an array
if class_ids:
mask = np.stack(instance_masks, axis=2).astype(np.bool)
class_ids = np.array(class_ids, dtype=np.int32)
return mask, class_ids
else:
# Call super class to return an empty mask
return super(CocoDataset, self).load_mask(image_id)
def image_reference(self, image_id):
"""Return a link to the image in the COCO Website."""
info = self.image_info[image_id]
if info["source"] == "coco":
return "http://cocodataset.org/#explore?id={}".format(info["id"])
else:
super(CocoDataset, self).image_reference(image_id)
# The following two functions are from pycocotools with a few changes.
def annToRLE(self, ann, height, width):
"""
Convert annotation which can be polygons, uncompressed RLE to RLE.
:return: binary mask (numpy 2D array)
"""
segm = ann['segmentation']
if isinstance(segm, list):
# polygon -- a single object might consist of multiple parts
# we merge all parts into one mask rle code
rles = maskUtils.frPyObjects(segm, height, width)
rle = maskUtils.merge(rles)
elif isinstance(segm['counts'], list):
# uncompressed RLE
rle = maskUtils.frPyObjects(segm, height, width)
else:
# rle
rle = ann['segmentation']
return rle
def annToMask(self, ann, height, width):
"""
Convert annotation which can be polygons, uncompressed RLE, or RLE to binary mask.
:return: binary mask (numpy 2D array)
"""
rle = self.annToRLE(ann, height, width)
m = maskUtils.decode(rle)
return m
############################################################
# COCO Evaluation
############################################################
def build_coco_results(dataset, image_ids, rois, class_ids, scores, masks):
"""Arrange resutls to match COCO specs in http://cocodataset.org/#format
"""
# If no results, return an empty list
if rois is None:
return []
results = []
for image_id in image_ids:
# Loop through detections
for i in range(rois.shape[0]):
class_id = class_ids[i]
score = scores[i]
bbox = np.around(rois[i], 1)
mask = masks[:, :, i]
result = {
"image_id": image_id,
"category_id": dataset.get_source_class_id(class_id, "coco"),
"bbox": [bbox[1], bbox[0], bbox[3] - bbox[1], bbox[2] - bbox[0]],
"score": score,
"segmentation": maskUtils.encode(np.asfortranarray(mask))
}
results.append(result)
return results
def evaluate_coco(model, dataset, coco, eval_type="bbox", limit=0, image_ids=None):
"""Runs official COCO evaluation.
dataset: A Dataset object with valiadtion data
eval_type: "bbox" or "segm" for bounding box or segmentation evaluation
limit: if not 0, it's the number of images to use for evaluation
"""
# Pick COCO images from the dataset
image_ids = image_ids or dataset.image_ids
# Limit to a subset
if limit:
image_ids = image_ids[:limit]
# Get corresponding COCO image IDs.
coco_image_ids = [dataset.image_info[id]["id"] for id in image_ids]
t_prediction = 0
t_start = time.time()
results = []
for i, image_id in enumerate(image_ids):
# Load image
image = dataset.load_image(image_id)
# Run detection
t = time.time()
r = model.detect([image], verbose=0)[0]
t_prediction += (time.time() - t)
# Convert results to COCO format
# Cast masks to uint8 because COCO tools errors out on bool
image_results = build_coco_results(dataset, coco_image_ids[i:i + 1],
r["rois"], r["class_ids"],
r["scores"],
r["masks"].astype(np.uint8))
results.extend(image_results)
# Load results. This modifies results with additional attributes.
coco_results = coco.loadRes(results)
# Evaluate
cocoEval = COCOeval(coco, coco_results, eval_type)
cocoEval.params.imgIds = coco_image_ids
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
print("Prediction time: {}. Average {}/image".format(
t_prediction, t_prediction / len(image_ids)))
print("Total time: ", time.time() - t_start)
############################################################
# Training
############################################################
if __name__ == '__main__':
import argparse
# Parse command line arguments
parser = argparse.ArgumentParser(
description='Train Mask R-CNN on MS COCO.')
parser.add_argument("command",
metavar="<command>",
help="'train' or 'evaluate' on MS COCO")
parser.add_argument('--dataset', required=True,
metavar="C:\\Users\\HP\\TEST\\Train",
help='Directory of the MS-COCO dataset')
parser.add_argument('--year', required=False,
default=DEFAULT_DATASET_YEAR,
metavar="<year>",
help='Year of the MS-COCO dataset (2014 or 2017) (default=2014)')
parser.add_argument('--model', required=False,
#metavar="C:\\Users\\HP\\mask_rcnn_coco.h5"
metavar="C:\\Users\\HP\\Mask_RCNN\\samples\\coco\\coco.py",
help="Path to weights .h5 file or 'coco'")
parser.add_argument('--logs', required=False,
default=DEFAULT_LOGS_DIR,
metavar="/path/to/logs/",
help='Logs and checkpoints directory (default=logs/)')
parser.add_argument('--limit', required=False,
default=500,
metavar="<image count>",
help='Images to use for evaluation (default=500)')
parser.add_argument('--download', required=False,
default=False,
metavar="<True|False>",
help='Automatically download and unzip MS-COCO files (default=False)',
type=bool)
args = parser.parse_args()
print("Command: ", args.command)
print("Model: ", args.model)
print("Dataset: ", args.dataset)
print("Year: ", args.year)
print("Logs: ", args.logs)
print("Auto Download: ", args.download)
# Configurations
if args.command == "train":
config = CocoConfig()
else:
class InferenceConfig(CocoConfig):
# Set batch size to 1 since we'll be running inference on
# one image at a time. Batch size = GPU_COUNT * IMAGES_PER_GPU
GPU_COUNT = 1
IMAGES_PER_GPU = 1
DETECTION_MIN_CONFIDENCE = 0
config = InferenceConfig()
config.display()
# Create model
if args.command == "train":
model = modellib.MaskRCNN(mode="training", config=config,
model_dir=args.logs)
else:
model = modellib.MaskRCNN(mode="inference", config=config,
model_dir=args.logs)
# Select weights file to load
if args.model.lower() == "coco":
model_path = COCO_MODEL_PATH
elif args.model.lower() == "last":
# Find last trained weights
model_path = model.find_last()
elif args.model.lower() == "imagenet":
# Start from ImageNet trained weights
model_path = model.get_imagenet_weights()
else:
model_path = args.model
# Load weights
print("Loading weights ", model_path)
model.load_weights(model_path, by_name=True)
# Train or evaluate
if args.command == "train":
# Training dataset. Use the training set and 35K from the
# validation set, as as in the Mask RCNN paper.
dataset_train = CocoDataset()
dataset_train.load_coco(args.dataset, "train", year=args.year, auto_download=args.download)
if args.year in '2014':
dataset_train.load_coco(args.dataset, "valminusminival", year=args.year, auto_download=args.download)
dataset_train.prepare()
# Validation dataset
dataset_val = CocoDataset()
val_type = "val" if args.year in '2017' else "minival"
dataset_val.load_coco(args.dataset, val_type, year=args.year, auto_download=args.download)
dataset_val.prepare()
# Image Augmentation
# Right/Left flip 50% of the time
augmentation = imgaug.augmenters.Fliplr(0.5)
# *** This training schedule is an example. Update to your needs ***
# Training - Stage 1
print("Training network heads")
model.train(dataset_train, dataset_val,
learning_rate=config.LEARNING_RATE,
epochs=40,
layers='heads',
augmentation=augmentation)
# Training - Stage 2
# Finetune layers from ResNet stage 4 and up
print("Fine tune Resnet stage 4 and up")
model.train(dataset_train, dataset_val,
learning_rate=config.LEARNING_RATE,
epochs=120,
layers='4+',
augmentation=augmentation)
# Training - Stage 3
# Fine tune all layers
print("Fine tune all layers")
model.train(dataset_train, dataset_val,
learning_rate=config.LEARNING_RATE / 10,
epochs=160,
layers='all',
augmentation=augmentation)
elif args.command == "evaluate":
# Validation dataset
dataset_val = CocoDataset()
val_type = "val" if args.year in '2017' else "minival"
coco = dataset_val.load_coco(args.dataset, val_type, year=args.year, return_coco=True,auto_download=args.download)
dataset_val.prepare()
print("Running COCO evaluation on {} images.".format(args.limit))
evaluate_coco(model, dataset_val, coco, "bbox", limit=int(args.limit))
else:
print("'{}' is not recognized. "
"Use 'train' or 'evaluate'".format(args.command))
Now after I saved this code as a .py file and executed the following command on my terminal:
(base) C:\Users\HP>python C:\Users\HP\Mask_RCNN\samples\coco\coco.py train --dataset=C:\Users\HP\Test\Train --model=coco
I got the following:
2020-12-21 00:41:06.252236: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2020-12-21 00:41:06.260248: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
(base) C:\Users\HP>python C:\Users\HP\Desktop\try.py train --dataset=C:\Users\HP\Test\Train --model=C:\Users\HP\mask_rcnn_coco.h5
2020-12-21 00:42:34.586446: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2020-12-21 00:42:34.594568: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
(base) C:\Users\HP>python C:\Users\HP\Mask_RCNN\samples\coco\coco.py train --dataset=C:\Users\HP\Test\Train --model=coco
2020-12-21 00:44:41.479421: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2020-12-21 00:44:41.490317: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Command: train
Model: coco
Dataset: C:\Users\HP\Test\Train
Year: 2014
Logs: C:\Mask_RCNN\logs
Auto Download: False
Configurations:
BACKBONE resnet101
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 2
BBOX_STD_DEV [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE None
DETECTION_MAX_INSTANCES 100
DETECTION_MIN_CONFIDENCE 0.7
DETECTION_NMS_THRESHOLD 0.3
FPN_CLASSIF_FC_LAYERS_SIZE 1024
GPU_COUNT 1
GRADIENT_CLIP_NORM 5.0
IMAGES_PER_GPU 2
IMAGE_MAX_DIM 1024
IMAGE_META_SIZE 93
IMAGE_MIN_DIM 800
IMAGE_MIN_SCALE 0
IMAGE_RESIZE_MODE square
IMAGE_SHAPE [1024 1024 3]
LEARNING_MOMENTUM 0.9
LEARNING_RATE 0.001
LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0}
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 coco
NUM_CLASSES 81
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 (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE 1
RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD 0.7
RPN_TRAIN_ANCHORS_PER_IMAGE 256
STEPS_PER_EPOCH 1000
TOP_DOWN_PYRAMID_SIZE 256
TRAIN_BN False
TRAIN_ROIS_PER_IMAGE 200
USE_MINI_MASK True
USE_RPN_ROIS True
VALIDATION_STEPS 50
WEIGHT_DECAY 0.0001
Traceback (most recent call last):
File "C:\Users\HP\Mask_RCNN\samples\coco\coco.py", line 456, in <module>
model_dir=args.logs)
File "C:\Users\HP\anaconda3\lib\site-packages\mrcnn\model.py", line 1832, in __init__
self.keras_model = self.build(mode=mode, config=config)
File "C:\Users\HP\anaconda3\lib\site-packages\mrcnn\model.py", line 1871, in build
x, K.shape(input_image)[1:3]))(input_gt_boxes)
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 952, in __call__
input_list)
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 869, in _infer_output_signature
keras_tensor.keras_tensor_from_tensor, outputs)
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\util\nest.py", line 659, in map_structure
structure[0], [func(*x) for x in entries],
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\util\nest.py", line 659, in <listcomp>
structure[0], [func(*x) for x in entries],
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\keras\engine\keras_tensor.py", line 606, in keras_tensor_from_tensor
out = keras_tensor_cls.from_tensor(tensor)
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\keras\engine\keras_tensor.py", line 205, in from_tensor
type_spec = type_spec_module.type_spec_from_value(tensor)
File "C:\Users\HP\anaconda3\lib\site-packages\tensorflow\python\framework\type_spec.py", line 554, in type_spec_from_value
(value, type(value).__name__))
TypeError: Could not build a TypeSpec for <KerasTensor: shape=(None, None, 4) dtype=float32 (created by layer 'tf.math.truediv')> with type KerasTensor