Update runCpu.sh

vision/runCpu.sh

-'''This script goes along the blog post
-"Building powerful image classification models using very little data"
-from blog.keras.io.
-It uses data that can be downloaded at:
-https://www.kaggle.com/c/dogs-vs-cats/data
-In our setup, we:
-- created a data/ folder
-- created train/ and validation/ subfolders inside data/
-- created cats/ and dogs/ subfolders inside train/ and validation/
-- put the cat pictures index 0-999 in data/train/cats
-- put the cat pictures index 1000-1400 in data/validation/cats
-- put the dogs pictures index 12500-13499 in data/train/dogs
-- put the dog pictures index 13500-13900 in data/validation/dogs
-So that we have 1000 training examples for each class, and 400 validation examples for each class.
-In summary, this is our directory structure:
-```
-data/
-    train/
-        dogs/
-            dog001.jpg
-            dog002.jpg
-            ...
-        cats/
-            cat001.jpg
-            cat002.jpg
-            ...
-    validation/
-        dogs/
-            dog001.jpg
-            dog002.jpg
-            ...
-        cats/
-            cat001.jpg
-            cat002.jpg
-            ...
-```
-'''
-import numpy as np
-from keras.preprocessing.image import ImageDataGenerator
-from keras.models import Sequential
-from keras.layers import Dropout, Flatten, Dense
-from keras import applications
+PRETRAINED_CHECKPOINT_DIR=/tflow/tmp/checkpoints
 
-# dimensions of our images.
-img_width, img_height = 150, 150
+OUTPUT_DIR=output
+DATA_DIR=data
+CAPTIONS_DIR="${DATA_DIR}/captions"
+IMG_TRAIN_DIR="${DATA_DIR}/val"
+IMG_VAL_DIR="${DATA_DIR}/val"
 
-top_model_weights_path = '/tflow/vgg16_weights.h5'
-train_data_dir = 'data/train'
-validation_data_dir = 'data/validation'
-nb_train_samples = 2000
-nb_validation_samples = 800
-epochs = 1
-batch_size = 16
 
+# Where the training (fine-tuned) checkpoint and logs will be saved to.
+TRAIN_DIR=models/inception_v3
 
-def save_bottlebeck_features():
-    datagen = ImageDataGenerator(rescale=1. / 255)
+# Where the dataset is saved to.
+DATASET_DIR=output/dataset
 
-    # build the VGG16 network
-    model = applications.VGG16(include_top=False, weights='imagenet')
+# Download the pre-trained checkpoint.
+if [ ! -d "$PRETRAINED_CHECKPOINT_DIR" ]; then
+  mkdir ${PRETRAINED_CHECKPOINT_DIR}
+fi
+if [ ! -f ${PRETRAINED_CHECKPOINT_DIR}/inception_v3.ckpt ]; then
+  wget http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz
+  tar -xvf inception_v3_2016_08_28.tar.gz
+  mv inception_v3.ckpt ${PRETRAINED_CHECKPOINT_DIR}/inception_v3.ckpt
+  rm inception_v3_2016_08_28.tar.gz
+fi
 
-    generator = datagen.flow_from_directory(
-        train_data_dir,
-        target_size=(img_width, img_height),
-        batch_size=batch_size,
-        class_mode=None,
-        shuffle=False)
-    bottleneck_features_train = model.predict_generator(
-        generator, nb_train_samples // batch_size)
-    np.save(open('bottleneck_features_train.npy', 'w'),
-            bottleneck_features_train)
 
-    generator = datagen.flow_from_directory(
-        validation_data_dir,
-        target_size=(img_width, img_height),
-        batch_size=batch_size,
-        class_mode=None,
-        shuffle=False)
-    bottleneck_features_validation = model.predict_generator(
-        generator, nb_validation_samples // batch_size)
-    np.save(open('bottleneck_features_validation.npy', 'w'),
-            bottleneck_features_validation)
+#prepare data
 
+#python prepro.py --train_image_dir="${IMG_TRAIN_DIR}"  --val_image_dir="${IMG_VAL_DIR}"  --train_captions_file="${CAPTIONS_DIR}/val.json" --val_captions_file="${CAPTIONS_DIR}/val.json" --output_dir="${OUTPUT_DIR}/tf" --word_counts_output_file="${OUTPUT_DIR}/word_counts.txt" 
 
-def train_top_model():
-    train_data = np.load(open('bottleneck_features_train.npy'))
-    train_labels = np.array(
-        [0] * (nb_train_samples / 2) + [1] * (nb_train_samples / 2))
+python train.py \
+  --input_file_pattern="${MSCOCO_DIR}/tf/val-?????-of-00256" \
+  --inception_checkpoint_file="${INCEPTION_CHECKPOINT}" \
+  --train_dir="${OUTPUT_DIR}/tf/val" \
+  --train_inception=false \
+  --number_of_steps=1000000
 
-    validation_data = np.load(open('bottleneck_features_validation.npy'))
-    validation_labels = np.array(
-        [0] * (nb_validation_samples / 2) + [1] * (nb_validation_samples / 2))
-
-    model = Sequential()
-    model.add(Flatten(input_shape=train_data.shape[1:]))
-    model.add(Dense(256, activation='relu'))
-    model.add(Dropout(0.5))
-    model.add(Dense(1, activation='sigmoid'))
-
-    model.compile(optimizer='rmsprop',
-                  loss='binary_crossentropy', metrics=['accuracy'])
-
-    model.fit(train_data, train_labels,
-              epochs=epochs,
-              batch_size=batch_size,
-              validation_data=(validation_data, validation_labels))
-    model.save_weights(top_model_weights_path)
-
-
-save_bottlebeck_features()
-train_top_model()