A platform for making deep learning work everywhere.
Documentation | Installation Instructions | Building PlaidML | Contributing | Troubleshooting | Reporting Issues
PlaidML is an advanced and portable tensor compiler for enabling deep learning on laptops, embedded devices, or other devices where the available computing hardware is not well supported or the available software stack contains unpalatable license restrictions.
PlaidML sits underneath common machine learning frameworks, enabling users to access any hardware supported by PlaidML. PlaidML supports Keras, ONNX, and nGraph.
As a component within the nGraph Compiler stack, PlaidML further extends the capabilities of specialized deep-learning hardware (especially GPUs,) and makes it both easier and faster to access or make use of subgraph-level optimizations that would otherwise be bounded by the compute limitations of the device.
As a component under Keras, PlaidML can accelerate training workloads with customized or automatically-generated Tile code. It works especially well on GPUs, and it doesn't require use of CUDA/cuDNN on Nvidia* hardware, while achieving comparable performance.
PlaidML works on all major operating systems: Linux, macOS, and Windows.
If you are using a hardware target not supported by PlaidML by default, such as Clover, check out the instructions at building PlaidML to build a custom configuration to support your hardware.
- Python (v2 supported, v3 recommended)
- OpenCL 1.2 or greater
See the troubleshooting documentation for common issues.
virtualenv plaidml
source plaidml/bin/activate
pip install plaidml-keras plaidbench
Choose which accelerator you'd like to use (many computers, especially laptops, have multiple):
plaidml-setup
Next, try benchmarking MobileNet inference performance:
plaidbench keras mobilenet
Or, try training MobileNet:
plaidbench --batch-size 16 keras --train mobilenet
We support a variety of operating systems and installation methods.
Plaidbench is a performance testing suite designed to help users compare the performance of different cards and different frameworks.
One of the great things about Keras is how easy it is to play with state of the art networks. Here's all the code you need to run VGG-19:
#!/usr/bin/env python
import numpy as np
import os
import time
os.environ["KERAS_BACKEND"] = "plaidml.keras.backend"
import keras
import keras.applications as kapp
from keras.datasets import cifar10
(x_train, y_train_cats), (x_test, y_test_cats) = cifar10.load_data()
batch_size = 8
x_train = x_train[:batch_size]
x_train = np.repeat(np.repeat(x_train, 7, axis=1), 7, axis=2)
model = kapp.VGG19()
model.compile(optimizer='sgd', loss='categorical_crossentropy',
metrics=['accuracy'])
print("Running initial batch (compiling tile program)")
y = model.predict(x=x_train, batch_size=batch_size)
# Now start the clock and run 10 batches
print("Timing inference...")
start = time.time()
for i in range(10):
y = model.predict(x=x_train, batch_size=batch_size)
print("Ran in {} seconds".format(time.time() - start))Either open a ticket on GitHub or join our slack workspace (#plaidml).
A comprehensive set of tests for each release are run against the hardware targets listed below.
-
AMD
- R9 Nano
- RX 480
- Vega 10
-
Intel
- HD4000
- HD Graphics 505
-
NVIDIA
- K80
- GT 640M
- GTX 1050
- GTX 1070
We support all of the Keras application networks from current versions of 2.x. Validated networks are tested for performance and correctness as part of our continuous integration system.
-
CNNs
- Inception v3
- ResNet50
- VGG19
- Xception
- MobileNet
- DenseNet
- ShuffleNet
-
LSTM
- examples/imdb_lstm.py (from keras)