mirror of
https://github.com/autistic-symposium/ml-ai-agents-py.git
synced 2025-08-18 03:00:16 -04:00
chores: refactor for the new ai research, add linter, gh action, etc (#27)
This commit is contained in:
Marina von Steinkirch, PhD
von-steinkirch
parent
fb4ab80dc3
commit
d5467e559f
40 changed files with 5177 additions and 2476 deletions
|
|
@ -1,105 +1,112 @@
|
|||
# Code derived from tensorflow/tensorflow/models/image/imagenet/classify_image.py
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
# Code derived from
|
||||
# tensorflow/tensorflow/models/image/imagenet/classify_image.py
|
||||
from __future__ import absolute_import, division, print_function
|
||||
|
||||
import math
|
||||
import os.path
|
||||
import sys
|
||||
import tarfile
|
||||
|
||||
import numpy as np
|
||||
from six.moves import urllib
|
||||
import tensorflow as tf
|
||||
import glob
|
||||
import scipy.misc
|
||||
import math
|
||||
import sys
|
||||
|
||||
import horovod.tensorflow as hvd
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
from six.moves import urllib
|
||||
|
||||
MODEL_DIR = '/tmp/imagenet'
|
||||
DATA_URL = 'http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz'
|
||||
MODEL_DIR = "/tmp/imagenet"
|
||||
DATA_URL = (
|
||||
"http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz"
|
||||
)
|
||||
softmax = None
|
||||
|
||||
config = tf.ConfigProto()
|
||||
config.gpu_options.visible_device_list = str(hvd.local_rank())
|
||||
sess = tf.Session(config=config)
|
||||
|
||||
# Call this function with list of images. Each of elements should be a
|
||||
|
||||
# Call this function with list of images. Each of elements should be a
|
||||
# numpy array with values ranging from 0 to 255.
|
||||
def get_inception_score(images, splits=10):
|
||||
# For convenience
|
||||
if len(images[0].shape) != 3:
|
||||
return 0, 0
|
||||
# For convenience
|
||||
if len(images[0].shape) != 3:
|
||||
return 0, 0
|
||||
|
||||
# Bypassing all the assertions so that we don't end prematuraly'
|
||||
# assert(type(images) == list)
|
||||
# assert(type(images[0]) == np.ndarray)
|
||||
# assert(len(images[0].shape) == 3)
|
||||
# assert(np.max(images[0]) > 10)
|
||||
# assert(np.min(images[0]) >= 0.0)
|
||||
inps = []
|
||||
for img in images:
|
||||
img = img.astype(np.float32)
|
||||
inps.append(np.expand_dims(img, 0))
|
||||
bs = 1
|
||||
preds = []
|
||||
n_batches = int(math.ceil(float(len(inps)) / float(bs)))
|
||||
for i in range(n_batches):
|
||||
sys.stdout.write(".")
|
||||
sys.stdout.flush()
|
||||
inp = inps[(i * bs) : min((i + 1) * bs, len(inps))]
|
||||
inp = np.concatenate(inp, 0)
|
||||
pred = sess.run(softmax, {"ExpandDims:0": inp})
|
||||
preds.append(pred)
|
||||
preds = np.concatenate(preds, 0)
|
||||
scores = []
|
||||
for i in range(splits):
|
||||
part = preds[
|
||||
(i * preds.shape[0] // splits) : ((i + 1) * preds.shape[0] // splits), :
|
||||
]
|
||||
kl = part * (np.log(part) - np.log(np.expand_dims(np.mean(part, 0), 0)))
|
||||
kl = np.mean(np.sum(kl, 1))
|
||||
scores.append(np.exp(kl))
|
||||
return np.mean(scores), np.std(scores)
|
||||
|
||||
# Bypassing all the assertions so that we don't end prematuraly'
|
||||
# assert(type(images) == list)
|
||||
# assert(type(images[0]) == np.ndarray)
|
||||
# assert(len(images[0].shape) == 3)
|
||||
# assert(np.max(images[0]) > 10)
|
||||
# assert(np.min(images[0]) >= 0.0)
|
||||
inps = []
|
||||
for img in images:
|
||||
img = img.astype(np.float32)
|
||||
inps.append(np.expand_dims(img, 0))
|
||||
bs = 1
|
||||
preds = []
|
||||
n_batches = int(math.ceil(float(len(inps)) / float(bs)))
|
||||
for i in range(n_batches):
|
||||
sys.stdout.write(".")
|
||||
sys.stdout.flush()
|
||||
inp = inps[(i * bs):min((i + 1) * bs, len(inps))]
|
||||
inp = np.concatenate(inp, 0)
|
||||
pred = sess.run(softmax, {'ExpandDims:0': inp})
|
||||
preds.append(pred)
|
||||
preds = np.concatenate(preds, 0)
|
||||
scores = []
|
||||
for i in range(splits):
|
||||
part = preds[(i * preds.shape[0] // splits):((i + 1) * preds.shape[0] // splits), :]
|
||||
kl = part * (np.log(part) - np.log(np.expand_dims(np.mean(part, 0), 0)))
|
||||
kl = np.mean(np.sum(kl, 1))
|
||||
scores.append(np.exp(kl))
|
||||
return np.mean(scores), np.std(scores)
|
||||
|
||||
# This function is called automatically.
|
||||
def _init_inception():
|
||||
global softmax
|
||||
if not os.path.exists(MODEL_DIR):
|
||||
os.makedirs(MODEL_DIR)
|
||||
filename = DATA_URL.split('/')[-1]
|
||||
filepath = os.path.join(MODEL_DIR, filename)
|
||||
if not os.path.exists(filepath):
|
||||
def _progress(count, block_size, total_size):
|
||||
sys.stdout.write('\r>> Downloading %s %.1f%%' % (
|
||||
filename, float(count * block_size) / float(total_size) * 100.0))
|
||||
sys.stdout.flush()
|
||||
filepath, _ = urllib.request.urlretrieve(DATA_URL, filepath, _progress)
|
||||
print()
|
||||
statinfo = os.stat(filepath)
|
||||
print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
|
||||
tarfile.open(filepath, 'r:gz').extractall(MODEL_DIR)
|
||||
with tf.gfile.FastGFile(os.path.join(
|
||||
MODEL_DIR, 'classify_image_graph_def.pb'), 'rb') as f:
|
||||
graph_def = tf.GraphDef()
|
||||
graph_def.ParseFromString(f.read())
|
||||
_ = tf.import_graph_def(graph_def, name='')
|
||||
# Works with an arbitrary minibatch size.
|
||||
pool3 = sess.graph.get_tensor_by_name('pool_3:0')
|
||||
ops = pool3.graph.get_operations()
|
||||
for op_idx, op in enumerate(ops):
|
||||
for o in op.outputs:
|
||||
shape = o.get_shape()
|
||||
shape = [s.value for s in shape]
|
||||
new_shape = []
|
||||
for j, s in enumerate(shape):
|
||||
if s == 1 and j == 0:
|
||||
new_shape.append(None)
|
||||
else:
|
||||
new_shape.append(s)
|
||||
o.set_shape(tf.TensorShape(new_shape))
|
||||
w = sess.graph.get_operation_by_name("softmax/logits/MatMul").inputs[1]
|
||||
logits = tf.matmul(tf.squeeze(pool3, [1, 2]), w)
|
||||
softmax = tf.nn.softmax(logits)
|
||||
global softmax
|
||||
if not os.path.exists(MODEL_DIR):
|
||||
os.makedirs(MODEL_DIR)
|
||||
filename = DATA_URL.split("/")[-1]
|
||||
filepath = os.path.join(MODEL_DIR, filename)
|
||||
if not os.path.exists(filepath):
|
||||
|
||||
def _progress(count, block_size, total_size):
|
||||
sys.stdout.write(
|
||||
"\r>> Downloading %s %.1f%%"
|
||||
% (filename, float(count * block_size) / float(total_size) * 100.0)
|
||||
)
|
||||
sys.stdout.flush()
|
||||
|
||||
filepath, _ = urllib.request.urlretrieve(DATA_URL, filepath, _progress)
|
||||
print()
|
||||
statinfo = os.stat(filepath)
|
||||
print("Succesfully downloaded", filename, statinfo.st_size, "bytes.")
|
||||
tarfile.open(filepath, "r:gz").extractall(MODEL_DIR)
|
||||
with tf.gfile.FastGFile(
|
||||
os.path.join(MODEL_DIR, "classify_image_graph_def.pb"), "rb"
|
||||
) as f:
|
||||
graph_def = tf.GraphDef()
|
||||
graph_def.ParseFromString(f.read())
|
||||
_ = tf.import_graph_def(graph_def, name="")
|
||||
# Works with an arbitrary minibatch size.
|
||||
pool3 = sess.graph.get_tensor_by_name("pool_3:0")
|
||||
ops = pool3.graph.get_operations()
|
||||
for op_idx, op in enumerate(ops):
|
||||
for o in op.outputs:
|
||||
shape = o.get_shape()
|
||||
shape = [s.value for s in shape]
|
||||
new_shape = []
|
||||
for j, s in enumerate(shape):
|
||||
if s == 1 and j == 0:
|
||||
new_shape.append(None)
|
||||
else:
|
||||
new_shape.append(s)
|
||||
o.set_shape(tf.TensorShape(new_shape))
|
||||
w = sess.graph.get_operation_by_name("softmax/logits/MatMul").inputs[1]
|
||||
logits = tf.matmul(tf.squeeze(pool3, [1, 2]), w)
|
||||
softmax = tf.nn.softmax(logits)
|
||||
|
||||
|
||||
if softmax is None:
|
||||
_init_inception()
|
||||
_init_inception()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue