Skip to content

Fix script about benchmarking humpback_whale model #1671

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 13, 2021
Merged

Fix script about benchmarking humpback_whale model #1671

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 19 additions & 13 deletions tests/tfhub/_tools.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,7 +213,7 @@ def check_discrepencies(out1, out2, threshold=1e-3):

def benchmark(url, dest, onnx_name, opset, imgs, verbose=True, threshold=1e-3,
signature=None, tag=None, output_name=None, ort_name=None,
optimize=True, convert_tflite=None):
optimize=True, convert_tflite=None, custom_tf=None):
"""
Runs a simple benchmark.
Goes through every steps (download, convert).
Expand Down Expand Up @@ -290,18 +290,21 @@ def benchmark(url, dest, onnx_name, opset, imgs, verbose=True, threshold=1e-3,
print("ORT", len(imgs), duration_ort)

# tensorflow
import tensorflow_hub as hub
from tensorflow import convert_to_tensor
if isinstance(imgs[0], OrderedDict):
imgs_tf = [
OrderedDict((k, convert_to_tensor(v)) for k, v in img.items())
for img in imgs]
if custom_tf is None:
import tensorflow_hub as hub
from tensorflow import convert_to_tensor
if isinstance(imgs[0], OrderedDict):
imgs_tf = [
OrderedDict((k, convert_to_tensor(v)) for k, v in img.items())
for img in imgs]
else:
imgs_tf = [convert_to_tensor(img) for img in imgs]
model = hub.load(url.split("?")[0])
if signature is not None:
model = model.signatures[signature]
results_tf, duration_tf = measure_time(model, imgs_tf)
else:
imgs_tf = [convert_to_tensor(img) for img in imgs]
model = hub.load(url.split("?")[0])
if signature is not None:
model = model.signatures[signature]
results_tf, duration_tf = measure_time(model, imgs_tf)
output, results_tf, duration_tf = custom_tf(tname)

if verbose:
print("TF", len(imgs), duration_tf)
Expand All @@ -310,7 +313,10 @@ def benchmark(url, dest, onnx_name, opset, imgs, verbose=True, threshold=1e-3,
print("ratio ORT=%r / TF=%r = %r" % (mean_ort, mean_tf, mean_ort / mean_tf))

# checks discrepencies
res = model(imgs_tf[0])
if custom_tf is None:
res = model(imgs_tf[0])
else:
res = output
if isinstance(res, dict):
if output_name is None:
if len(res) != 1:
Expand Down
100 changes: 36 additions & 64 deletions tests/tfhub/tfhub_humpback_whale.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,81 +1,53 @@
# SPDX-License-Identifier: Apache-2.0
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
import pickle
import numpy
from onnxruntime import InferenceSession
from _tools import generate_random_images, benchmark
from _tools import generate_random_images, benchmark, measure_time
import tensorflow as tf
import tensorflow_hub as hub


def main(opset=13):
url = "https://tfhub.dev/google/humpback_whale/1?tf-hub-format=compressed"
dest = "tf-humpback-whale"
name = "humpback-whale"
onnx_name = os.path.join(dest, "%s-%d.onnx" % (name, opset))

kind = "function"
if kind == "function":
import tensorflow as tf
import tensorflow_hub as hub
import tf2onnx
model = hub.load('https://tfhub.dev/google/humpback_whale/1')
FILENAME = 'gs://bioacoustics-www1/sounds/Cross_02_060203_071428.d20_7.wav'
waveform, sample_rate = tf.audio.decode_wav(tf.io.read_file(FILENAME))
waveform = tf.expand_dims(waveform, 0) # makes a batch of size 1
context_step_samples = tf.cast(sample_rate, tf.int64)
print(waveform.dtype, waveform.shape, sample_rate.dtype, sample_rate.shape, sample_rate)

spec = (tf.TensorSpec((None, ) + waveform.shape[-2:], tf.float32, name="waveform"),
tf.TensorSpec((1, 1), tf.int64, name="context_step_samples"))
inputs = {'waveform': waveform.numpy(),
'context_step_samples': context_step_samples.numpy()}

tf2onnx.convert.from_function(
model.signatures['score'], input_signature=spec, opset=13, output_path=onnx_name)
# AttributeError: '_WrapperFunction' object has no attribute 'get_concrete_function'

sess = InferenceSession(onnx_name)
got = sess.run(None, inputs)
print(got)

score_fn = model.signatures['score']
scores = score_fn(waveform=waveform, context_step_samples=context_step_samples)

if kind == "keras":
import tensorflow as tf
import tensorflow_hub as hub
import tf2onnx
model = hub.load('https://tfhub.dev/google/humpback_whale/1').model
FILENAME = 'gs://bioacoustics-www1/sounds/Cross_02_060203_071428.d20_7.wav'
waveform, sample_rate = tf.audio.decode_wav(tf.io.read_file(FILENAME))
waveform = tf.expand_dims(waveform, 0) # makes a batch of size 1
context_step_samples = tf.cast(sample_rate, tf.int64)
print(waveform.dtype, waveform.shape, sample_rate.dtype, sample_rate.shape, sample_rate)

spec = (tf.TensorSpec((None, ) + waveform.shape[-2:], tf.float32, name="waveform"),
tf.TensorSpec((1, 1), tf.int64, name="context_step_samples"))
inputs = {'waveform': waveform.numpy(),
'context_step_samples': context_step_samples.numpy()}

tf2onnx.convert.from_keras(model, input_signature=spec, opset=13, output_path=onnx_name)
# AttributeError: '_UserObject' object has no attribute 'output_names'

sess = InferenceSession(onnx_name)
got = sess.run(None, inputs)
print(got)

print("[download data]")
FILENAME = 'gs://bioacoustics-www1/sounds/Cross_02_060203_071428.d20_7.wav'
pkl_name = os.path.join(dest, "data.pkl")
if not os.path.exists(pkl_name):
with open(pkl_name, "wb") as f:
waveform, sample_rate = tf.audio.decode_wav(tf.io.read_file(FILENAME))
waveform = tf.expand_dims(waveform, 0) # makes a batch of size 1
context_step_samples = tf.cast(sample_rate, tf.int64)
data = dict(waveform=waveform, context_step_samples=context_step_samples)
pickle.dump(data, f)
else:
with open(pkl_name, "rb") as f:
data = pickle.load(f)
waveform = data["waveform"]
context_step_samples = data["context_step_samples"]
print("[data] done. context_step_samples=", context_step_samples.numpy())

def benchmark_custom(local_name):
model = hub.load(local_name)
score_fn = model.signatures['score']
scores = score_fn(waveform=waveform, context_step_samples=context_step_samples)
imgs_tf = [dict(waveform=waveform, context_step_samples=context_step_samples)]
results_tf, duration_tf = measure_time(
lambda inputs: score_fn(**inputs), imgs_tf)
return scores, results_tf, duration_tf

if kind == 'cmd':
imgs = generate_random_images(shape=(1, 10000, 1), scale=1.)
inputs = [dict(waveform=img,
context_step_samples=numpy.array(512, dtype=numpy.int64))
for img in imgs]
benchmark(url, dest, onnx_name, opset, inputs, optimize=False,
signature='score')
# onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException:
# [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'StatefulPartitionedCall/Reshape_1' Status Message: C:\xadupre\microsoft_xadupre\onnxruntime\onnxruntime\core\providers\cpu\tensor\reshape_helper.h:42 onnxruntime::ReshapeHelper::ReshapeHelper gsl::narrow_cast<int64_t>(input_shape.Size()) == size was false. The input tensor cannot be reshaped to the requested shape.
# Input shape:{0,1}, requested shape:{1,1,1}
imgs = generate_random_images(shape=(1, 750000, 1), scale=1., n=2)
inputs = [dict(waveform=waveform.numpy(),
context_step_samples=numpy.array(
context_step_samples.numpy(), dtype=numpy.int64))]
benchmark(url, dest, onnx_name, opset, inputs, optimize=False,
signature='score', custom_tf=benchmark_custom)


if __name__ == "__main__":
main()
with tf.device('/CPU:0'):
main()