Last active
July 26, 2020 01:21
-
-
Save shang-vikas/f25e13bfa5425258eb47c91d8739536b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## <font color=brown>Simple Graph Execution</font>" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"## import necessary stuff\n", | |
"import tensorflow as tf\n", | |
"import numpy as np\n", | |
"import os,sys\n", | |
"import time" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### Building simple DNN Model and feeding the numpy/pandas data" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"#### Simple MNIST Model of Dense layers" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"INFO:tensorflow:Using default config.\n", | |
"WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmpvcgi43dc\n", | |
"INFO:tensorflow:Using config: {'_model_dir': '/tmp/tmpvcgi43dc', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': None, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x7f9ec826ce10>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}\n" | |
] | |
} | |
], | |
"source": [ | |
"## defining the type of features columns to be used on model.\n", | |
"feature_column = [tf.feature_column.numeric_column(key='image',shape=(784,))]\n", | |
"\n", | |
"##defining the model\n", | |
"model = tf.estimator.DNNClassifier([100,100],n_classes=10,feature_columns=feature_column)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"heading_collapsed": true | |
}, | |
"source": [ | |
"### Same Mnist Model using TFRecords" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": { | |
"hidden": true | |
}, | |
"outputs": [], | |
"source": [ | |
"mnist_tfrecord_path = os.path.abspath('./mnist_train.tfrecords')" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"hidden": true | |
}, | |
"source": [ | |
"'''Oh crap! I forgot the feature names of tfrecords!!\n", | |
"A hack for this would be this line of code in bash \"head -n10 mnist_train.tfrecords\".\n", | |
"Just look for the feature name here.'''\n" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": { | |
"hidden": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def _parse_(serialized_example):\n", | |
" feature = {'image_raw':tf.FixedLenFeature([],tf.string),\n", | |
" 'label':tf.FixedLenFeature([],tf.int64)}\n", | |
" example = tf.parse_single_example(serialized_example,feature)\n", | |
" image = tf.decode_raw(example['image_raw'],tf.int64) #remember to parse in int64. float will raise error\n", | |
" label = tf.cast(example['label'],tf.int32)\n", | |
" return (dict({'image':image}),label)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": { | |
"hidden": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def tfrecord_train_input_fn(batch_size=32):\n", | |
" tfrecord_dataset = tf.data.TFRecordDataset(mnist_tfrecord_path)\n", | |
" tfrecord_dataset = tfrecord_dataset.map(lambda x:_parse_(x)).shuffle(True) \\\n", | |
" .batch(batch_size)\n", | |
" tfrecord_iterator = tfrecord_dataset.make_one_shot_iterator()\n", | |
" return tfrecord_iterator.get_next()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": { | |
"hidden": true | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"INFO:tensorflow:Calling model_fn.\n", | |
"INFO:tensorflow:Done calling model_fn.\n", | |
"INFO:tensorflow:Create CheckpointSaverHook.\n", | |
"INFO:tensorflow:Graph was finalized.\n", | |
"INFO:tensorflow:Running local_init_op.\n", | |
"INFO:tensorflow:Done running local_init_op.\n", | |
"INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmpjfa3etpe/model.ckpt.\n", | |
"INFO:tensorflow:loss = 3407.3716, step = 0\n", | |
"INFO:tensorflow:global_step/sec: 458.111\n", | |
"INFO:tensorflow:loss = 49.886246, step = 100 (0.219 sec)\n", | |
"INFO:tensorflow:Saving checkpoints for 200 into /tmp/tmpjfa3etpe/model.ckpt.\n", | |
"INFO:tensorflow:Loss for final step: 35.36163.\n" | |
] | |
}, | |
{ | |
"data": { | |
"text/plain": [ | |
"<tensorflow.python.estimator.canned.dnn.DNNClassifier at 0x7fcada6accf8>" | |
] | |
}, | |
"execution_count": 6, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"model.train(lambda:tfrecord_train_input_fn(32),steps=200)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### *What if i have the raw Images on disk*???" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"'''Here we need to use from_tensor_slices function of DATASET API again.'''" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# path = os.path.abspath('./digit-recognizer/train/')\n", | |
"\n", | |
"f = !ls ./digit-recognizer/train/" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
" def _ondisk_parse_(filename):\n", | |
" filename = tf.cast([filename],tf.string)\n", | |
" label = tf.string_split([tf.string_split(filename,'_').values[1]],'.').values[0]\n", | |
" label = tf.string_to_number([label],tf.int32)\n", | |
" path = os.path.abspath('./digit-recognizer/train//')\n", | |
" path = tf.cast([path],tf.string)\n", | |
" final_path = tf.string_join((path,tf.cast(['/'],tf.string),filename))\n", | |
" image_string = tf.read_file(final_path[0])\n", | |
" image = tf.image.decode_jpeg(image_string)\n", | |
" image = tf.cast(image,tf.int8)\n", | |
" image = tf.cast(image,tf.float32)\n", | |
" image_reshaped = tf.reshape(image,(784,))\n", | |
" return (dict({'image':image}),label)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"def ondisk_train_input_fn(filenames,batch_size=32):\n", | |
" dataset = tf.data.Dataset.from_tensor_slices(filenames)\n", | |
" dataset = dataset.map(lambda x:_ondisk_parse_(x)).shuffle(True).batch(batch_size)\n", | |
" ondisk_iterator = dataset.make_one_shot_iterator()\n", | |
" \n", | |
" return ondisk_iterator.get_next()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"INFO:tensorflow:Calling model_fn.\n", | |
"INFO:tensorflow:Done calling model_fn.\n", | |
"INFO:tensorflow:Create CheckpointSaverHook.\n", | |
"INFO:tensorflow:Graph was finalized.\n", | |
"INFO:tensorflow:Running local_init_op.\n", | |
"INFO:tensorflow:Done running local_init_op.\n", | |
"INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmpvcgi43dc/model.ckpt.\n", | |
"INFO:tensorflow:loss = 1007.99396, step = 0\n", | |
"INFO:tensorflow:Saving checkpoints for 2 into /tmp/tmpvcgi43dc/model.ckpt.\n", | |
"INFO:tensorflow:Loss for final step: 3291.0413.\n" | |
] | |
}, | |
{ | |
"data": { | |
"text/plain": [ | |
"<tensorflow.python.estimator.canned.dnn.DNNClassifier at 0x7f9ec826ccf8>" | |
] | |
}, | |
"execution_count": 6, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"model.train(lambda:ondisk_train_input_fn(f,32),steps=2)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"INFO:tensorflow:Calling model_fn.\n", | |
"INFO:tensorflow:Done calling model_fn.\n", | |
"INFO:tensorflow:Create CheckpointSaverHook.\n", | |
"INFO:tensorflow:Graph was finalized.\n", | |
"INFO:tensorflow:Restoring parameters from /tmp/tmpvcgi43dc/model.ckpt-2\n", | |
"INFO:tensorflow:Running local_init_op.\n", | |
"INFO:tensorflow:Done running local_init_op.\n", | |
"INFO:tensorflow:Saving checkpoints for 2 into /tmp/tmpvcgi43dc/model.ckpt.\n", | |
"INFO:tensorflow:loss = 7812.8594, step = 2\n", | |
"INFO:tensorflow:global_step/sec: 138.149\n", | |
"INFO:tensorflow:loss = 76.17598, step = 102 (0.725 sec)\n", | |
"INFO:tensorflow:Saving checkpoints for 202 into /tmp/tmpvcgi43dc/model.ckpt.\n", | |
"INFO:tensorflow:Loss for final step: 74.08304.\n" | |
] | |
}, | |
{ | |
"data": { | |
"text/plain": [ | |
"<tensorflow.python.estimator.canned.dnn.DNNClassifier at 0x7f9ec826ccf8>" | |
] | |
}, | |
"execution_count": 7, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"model.train(lambda:ondisk_train_input_fn(f,32),steps=200)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.6.5" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment