obeshor

obeshor

# Install nightly package for some functionalities that aren't in alpha
!pip install tensorflow-gpu==2.0.0-beta1
# Install TF Hub for TF2
!pip install 'tensorflow-hub == 0.5'

from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf
import tensorflow_hub as hub

from tensorflow.keras.layers import Dense, Flatten, Conv2D

obeshor

#Load data
zip_file=tf.keras.utils.get_file(origin='https://storage.googleapis.com/plantdata/PlantVillage.zip', 
 fname='PlantVillage.zip', extract=True)
#Create the training and validation directories
data_dir = os.path.join(os.path.dirname(zip_file), 'PlantVillage')
train_dir = os.path.join(data_dir, 'train')
validation_dir = os.path.join(data_dir, 'validation')

obeshor

!wget https://github.com/obeshor/Plant-Diseases-Detector/archive/master.zip
!unzip master.zip;
import json
with open('Plant-Diseases-Detector-master/categories.json', 'r') as f:
    cat_to_name = json.load(f)
    classes = list(cat_to_name.values())
    
print (classes)

obeshor

module_selection = ("inception_v3", 299, 2048) #@param ["(\"mobilenet_v2\", 224, 1280)", "(\"inception_v3\", 299, 2048)"] {type:"raw", allow-input: true}
handle_base, pixels, FV_SIZE = module_selection
MODULE_HANDLE ="https://tfhub.dev/google/tf2- preview/{}/feature_vector/2".format(handle_base)
IMAGE_SIZE = (pixels, pixels)
BATCH_SIZE = 64 #@param {type:"integer"}

obeshor

# Inputs are suitably resized for the selected module.
validation_datagen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)
validation_generator = validation_datagen.flow_from_directory(
    validation_dir, 
    shuffle=False, 
    seed=42,
    color_mode="rgb", 
    class_mode="categorical",
    target_size=IMAGE_SIZE,
    batch_size=BATCH_SIZE)

obeshor

feature_extractor = hub.KerasLayer(MODULE_HANDLE,
                                   input_shape=IMAGE_SIZE+(3,),
                                   output_shape=[FV_SIZE])
do_fine_tuning = False #@param {type:"boolean"}
 if do_fine_tuning:
    feature_extractor.trainable = True
    # unfreeze some layers of base network for fine-tuning
    for layer in feature_extractor.layers[-30:]:
       layer.trainable =True
  

obeshor

|#Compile model specifying the optimizer learning rate
LEARNING_RATE = 0.001 #@param {type:"number"}
model.compile(
   optimizer=tf.keras.optimizers.Adam(lr=LEARNING_RATE), 
   loss='categorical_crossentropy',
   metrics=['accuracy'])

obeshor

EPOCHS=10 #@param {type:"integer"}
STEPS_EPOCHS = train_generator.samples//train_generator.batch_size
VALID_STEPS=validation_generator.samples//validation_generator.batch_size
history = model.fit_generator( 
          train_generator,
          steps_per_epoch=STEPS_EPOCHS,
          epochs=EPOCHS,
          validation_data=validation_generator,
          validation_steps=VALID_STEPS)

obeshor

import matplotlib.pylab as plt
import numpy as np
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs_range = range(EPOCHS)
plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')