TensorFlow(pb) to TensorRT(uff)

Posted on | In |

[TOC]

Uff To TensorRT Engine

This sample uses a UFF ResNet50 Model to create a TensorRT Inference Engine

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
# This sample uses a UFF ResNet50 Model to create a TensorRT Inference Engine
import random
from PIL import Image
import numpy as np

import pycuda.driver as cuda
# This import causes pycuda to automatically manage CUDA context creation and cleanup.
import pycuda.autoinit

import tensorrt as trt

import sys, os
sys.path.insert(1, os.path.join(sys.path[0], ".."))
import common

class ModelData(object):
    MODEL_PATH = "resnet50-infer-5.uff"
    INPUT_NAME = "input"
    INPUT_SHAPE = (3, 224, 224)
    OUTPUT_NAME = "GPU_0/tower_0/Softmax"
    # We can convert TensorRT data types to numpy types with trt.nptype()
    DTYPE = trt.float32

# You can set the logger severity higher to suppress messages (or lower to display more messages).
TRT_LOGGER = trt.Logger(trt.Logger.WARNING)

# Allocate host and device buffers, and create a stream.
def allocate_buffers(engine):
    # Determine dimensions and create page-locked memory buffers (i.e. won't be swapped to disk) to hold host inputs/outputs.
    h_input = cuda.pagelocked_empty(trt.volume(engine.get_binding_shape(0)), dtype=trt.nptype(ModelData.DTYPE))
    h_output = cuda.pagelocked_empty(trt.volume(engine.get_binding_shape(1)), dtype=trt.nptype(ModelData.DTYPE))
    # Allocate device memory for inputs and outputs.
    d_input = cuda.mem_alloc(h_input.nbytes)
    d_output = cuda.mem_alloc(h_output.nbytes)
    # Create a stream in which to copy inputs/outputs and run inference.
    stream = cuda.Stream()
    return h_input, d_input, h_output, d_output, stream

def do_inference(context, h_input, d_input, h_output, d_output, stream):
    # Transfer input data to the GPU.
    cuda.memcpy_htod_async(d_input, h_input, stream)
    # Run inference.
    context.execute_async(bindings=[int(d_input), int(d_output)], stream_handle=stream.handle)
    # Transfer predictions back from the GPU.
    cuda.memcpy_dtoh_async(h_output, d_output, stream)
    # Synchronize the stream
    stream.synchronize()

# The UFF path is used for TensorFlow models. You can convert a frozen TensorFlow graph to UFF using the included convert-to-uff utility.
def build_engine_uff(model_file):
    # You can set the logger severity higher to suppress messages (or lower to display more messages).
    with trt.Builder(TRT_LOGGER) as builder, builder.create_network() as network, trt.UffParser() as parser:
        # Workspace size is the maximum amount of memory available to the builder while building an engine.
        # It should generally be set as high as possible.
        builder.max_workspace_size = common.GiB(1)
        # We need to manually register the input and output nodes for UFF.
        parser.register_input(ModelData.INPUT_NAME, ModelData.INPUT_SHAPE)
        parser.register_output(ModelData.OUTPUT_NAME)
        # Load the UFF model and parse it in order to populate the TensorRT network.
        parser.parse(model_file, network)
        # Build and return an engine.
        return builder.build_cuda_engine(network)

def load_normalized_test_case(test_image, pagelocked_buffer):
    # Converts the input image to a CHW Numpy array
    def normalize_image(image):
        # Resize, antialias and transpose the image to CHW.
        c, h, w = ModelData.INPUT_SHAPE
        return np.asarray(image.resize((w, h), Image.ANTIALIAS)).transpose([2, 0, 1]).astype(trt.nptype(ModelData.DTYPE)).ravel()

    # Normalize the image and copy to pagelocked memory.
    np.copyto(pagelocked_buffer, normalize_image(Image.open(test_image)))
    return test_image

def main():
    # Set the data path to the directory that contains the trained models and test images for inference.
    data_path, data_files = common.find_sample_data(description="Runs a ResNet50 network with a TensorRT inference engine.", subfolder="resnet50", find_files=["binoculars.jpeg", "reflex_camera.jpeg", "tabby_tiger_cat.jpg", ModelData.MODEL_PATH, "class_labels.txt"])
    # Get test images, models and labels.
    test_images = data_files[0:3]
    uff_model_file, labels_file = data_files[3:]
    labels = open(labels_file, 'r').read().split('\n')

    # Build a TensorRT engine.
    with build_engine_uff(uff_model_file) as engine:
        # Inference is the same regardless of which parser is used to build the engine, since the model architecture is the same.
        # Allocate buffers and create a CUDA stream.
        h_input, d_input, h_output, d_output, stream = allocate_buffers(engine)
        # Contexts are used to perform inference.
        with engine.create_execution_context() as context:
            # Load a normalized test case into the host input page-locked buffer.
            test_image = random.choice(test_images)
            test_case = load_normalized_test_case(test_image, h_input)
            # Run the engine. The output will be a 1D tensor of length 1000, where each value represents the
            # probability that the image corresponds to that label
            do_inference(context, h_input, d_input, h_output, d_output, stream)
            # We use the highest probability as our prediction. Its index corresponds to the predicted label.
            pred = labels[np.argmax(h_output)]
            if "_".join(pred.split()) in os.path.splitext(os.path.basename(test_case))[0]:
                print("Correctly recognized " + test_case + " as " + pred)
            else:
                print("Incorrectly recognized " + test_case + " as " + pred)

if __name__ == '__main__':
    main()