!pip install tensorflow=="2.6.0"

import os
import pathlib

# Clone the tensorflow models repository if it doesn't already exist
if "models" in pathlib.Path.cwd().parts:
  while "models" in pathlib.Path.cwd().parts:
    os.chdir('..')
elif not pathlib.Path('models').exists():
  !git clone --depth 1 https://github.com/tensorflow/models

# Install the Object Detection API
%%bash
cd models/research/
protoc object_detection/protos/*.proto --python_out=.
cp object_detection/packages/tf2/setup.py .
python -m pip install .

#run model builder test
!python /content/models/research/object_detection/builders/model_builder_tf2_test.py

# Install Kaggle API
!pip install -q kaggle
!pip install -q kaggle-cli

# only for google colab
import os
os.environ['KAGGLE_USERNAME'] = "<username>" 
os.environ['KAGGLE_KEY'] = "<key>"

!kaggle datasets download -d tannergi/microcontroller-detection --unzip

!mv "Microcontroller Detection" microcontroller-detection

!wget https://raw.githubusercontent.com/TannerGilbert/Tensorflow-Object-Detection-API-Train-Model/master/generate_tfrecord.py

!wget https://raw.githubusercontent.com/TannerGilbert/Tensorflow-Object-Detection-API-Train-Model/master/training/labelmap.pbtxt

!python generate_tfrecord.py --csv_input=microcontroller-detection/train_labels.csv --image_dir=microcontroller-detection/train --output_path=train.record
!python generate_tfrecord.py --csv_input=microcontroller-detection/test_labels.csv --image_dir=microcontroller-detection/test --output_path=test.record

train_record_path = '/content/train.record'
test_record_path = '/content/test.record'
labelmap_path = '/content/labelmap.pbtxt'

batch_size = 16
num_steps = 8000
num_eval_steps = 1000

!wget http://download.tensorflow.org/models/object_detection/tf2/20200711/efficientdet_d0_coco17_tpu-32.tar.gz
!tar -xf efficientdet_d0_coco17_tpu-32.tar.gz

fine_tune_checkpoint = 'efficientdet_d0_coco17_tpu-32/checkpoint/ckpt-0'

!wget https://raw.githubusercontent.com/tensorflow/models/master/research/object_detection/configs/tf2/ssd_efficientdet_d0_512x512_coco17_tpu-8.config

base_config_path = 'ssd_efficientdet_d0_512x512_coco17_tpu-8.config'

# edit configuration file (from https://colab.research.google.com/drive/1sLqFKVV94wm-lglFq_0kGo2ciM0kecWD)

import re

with open(base_config_path) as f:
    config = f.read()

with open('model_config.config', 'w') as f:
  
  # Set labelmap path
  config = re.sub('label_map_path: ".*?"', 
             'label_map_path: "{}"'.format(labelmap_path), config)
  
  # Set fine_tune_checkpoint path
  config = re.sub('fine_tune_checkpoint: ".*?"',
                  'fine_tune_checkpoint: "{}"'.format(fine_tune_checkpoint), config)
  
  # Set train tf-record file path
  config = re.sub('(input_path: ".*?)(PATH_TO_BE_CONFIGURED/train)(.*?")', 
                  'input_path: "{}"'.format(train_record_path), config)
  
  # Set test tf-record file path
  config = re.sub('(input_path: ".*?)(PATH_TO_BE_CONFIGURED/val)(.*?")', 
                  'input_path: "{}"'.format(test_record_path), config)
  
  # Set number of classes.
  config = re.sub('num_classes: [0-9]+',
                  'num_classes: {}'.format(4), config)
  
  # Set batch size
  config = re.sub('batch_size: [0-9]+',
                  'batch_size: {}'.format(batch_size), config)
  
  # Set training steps
  config = re.sub('num_steps: [0-9]+',
                  'num_steps: {}'.format(num_steps), config)
  
  # Set fine-tune checkpoint type to detection
  config = re.sub('fine_tune_checkpoint_type: "classification"', 
             'fine_tune_checkpoint_type: "{}"'.format('detection'), config)
  
  f.write(config)

%cat model_config.config

model_dir = 'training/'
pipeline_config_path = 'model_config.config'

!python /content/models/research/object_detection/model_main_tf2.py \
    --pipeline_config_path={pipeline_config_path} \
    --model_dir={model_dir} \
    --alsologtostderr \
    --num_train_steps={num_steps} \
    --sample_1_of_n_eval_examples=1 \
    --num_eval_steps={num_eval_steps}

%load_ext tensorboard
%tensorboard --logdir '/content/training/train'

output_directory = 'inference_graph'

!python /content/models/research/object_detection/exporter_main_v2.py \
    --trained_checkpoint_dir {model_dir} \
    --output_directory {output_directory} \
    --pipeline_config_path {pipeline_config_path}

from google.colab import files
files.download(f'/content/{output_directory}/saved_model/saved_model.pb') 

import io
import os
import scipy.misc
import numpy as np
import six
import time
import glob
from IPython.display import display

from six import BytesIO

import matplotlib
import matplotlib.pyplot as plt
from PIL import Image, ImageDraw, ImageFont

import tensorflow as tf
from object_detection.utils import ops as utils_ops
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

%matplotlib inline

def load_image_into_numpy_array(path):
  """Load an image from file into a numpy array.

  Puts image into numpy array to feed into tensorflow graph.
  Note that by convention we put it into a numpy array with shape
  (height, width, channels), where channels=3 for RGB.

  Args:
    path: a file path (this can be local or on colossus)

  Returns:
    uint8 numpy array with shape (img_height, img_width, 3)
  """
  img_data = tf.io.gfile.GFile(path, 'rb').read()
  image = Image.open(BytesIO(img_data))
  (im_width, im_height) = image.size
  return np.array(image.getdata()).reshape(
      (im_height, im_width, 3)).astype(np.uint8)

category_index = label_map_util.create_category_index_from_labelmap(labelmap_path, use_display_name=True)

tf.keras.backend.clear_session()
model = tf.saved_model.load(f'/content/{output_directory}/saved_model')

def run_inference_for_single_image(model, image):
  image = np.asarray(image)
  # The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
  input_tensor = tf.convert_to_tensor(image)
  # The model expects a batch of images, so add an axis with `tf.newaxis`.
  input_tensor = input_tensor[tf.newaxis,...]

  # Run inference
  model_fn = model.signatures['serving_default']
  output_dict = model_fn(input_tensor)

  # All outputs are batches tensors.
  # Convert to numpy arrays, and take index [0] to remove the batch dimension.
  # We're only interested in the first num_detections.
  num_detections = int(output_dict.pop('num_detections'))
  output_dict = {key:value[0, :num_detections].numpy() 
                 for key,value in output_dict.items()}
  output_dict['num_detections'] = num_detections

  # detection_classes should be ints.
  output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)
   
  # Handle models with masks:
  if 'detection_masks' in output_dict:
    # Reframe the the bbox mask to the image size.
    detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
              output_dict['detection_masks'], output_dict['detection_boxes'],
               image.shape[0], image.shape[1])      
    detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5,
                                       tf.uint8)
    output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()
    
  return output_dict

for image_path in glob.glob('microcontroller-detection/test/*.jpg'):
  image_np = load_image_into_numpy_array(image_path)
  output_dict = run_inference_for_single_image(model, image_np)
  vis_util.visualize_boxes_and_labels_on_image_array(
      image_np,
      output_dict['detection_boxes'],
      output_dict['detection_classes'],
      output_dict['detection_scores'],
      category_index,
      instance_masks=output_dict.get('detection_masks_reframed', None),
      use_normalized_coordinates=True,
      line_thickness=8)
  display(Image.fromarray(image_np))