apivovarov

#!/usr/bin/env python3

import nnvm
import tvm
import numpy as np

from mxnet.gluon.model_zoo.vision import get_model

batch_size = 1
image_shape = (3, 224, 224)

apivovarov

target: opencl -device=mali -model=unknown , opt_level: 3 , data_shape: (1, 3, 224, 224)
Compiling...
Cannot find config for target=opencl -device=mali -model=unknown, workload=('conv2d', (1, 3, 224, 224, 'float32'), (64, 3, 3, 3, 'float32'), (2, 2), (0, 0), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Traceback (most recent call last):
  File "./compile-cl.py", line 30, in <module>
    graph, lib, params = nnvm.compiler.build(sym, target, shape={"data": data_shape}, params=params)
  File "/usr/local/lib/python3.5/dist-packages/nnvm-0.8.0-py3.5.egg/nnvm/compiler/build_module.py", line 281, in build
    graph = optimize(graph, shape, dtype, layout)
  File "/usr/local/lib/python3.5/dist-packages/nnvm-0.8.0-py3.5.egg/nnvm/compiler/build_module.py", line 176, in optimize
    graph = graph.apply(["InferShape", "SimplifyInference"])

apivovarov

target: opencl -device=mali -model=unknown , opt_level: 3 , data_shape: (1, 3, 224, 224)
Compiling...
Traceback (most recent call last):
  File "./compile-cl.py", line 32, in <module>
    graph, lib, params = nnvm.compiler.build(sym, target, shape={"data": data_shape}, params=params)
  File "/usr/local/lib/python3.5/dist-packages/nnvm-0.8.0-py3.5.egg/nnvm/compiler/build_module.py", line 281, in build
    graph = optimize(graph, shape, dtype, layout)
  File "/usr/local/lib/python3.5/dist-packages/nnvm-0.8.0-py3.5.egg/nnvm/compiler/build_module.py", line 176, in optimize
    graph = graph.apply(["InferShape", "SimplifyInference"])
  File "/usr/local/lib/python3.5/dist-packages/nnvm-0.8.0-py3.5.egg/nnvm/graph.py", line 234, in apply

apivovarov

import nnvm
import tvm
import numpy as np

from mxnet.gluon.model_zoo.vision import get_model

batch_size = 1
image_shape = (3, 224, 224)
data_shape = (batch_size,) + image_shape
model_name = 'resnet18_v1' 

apivovarov

import nnvm
import tvm
import numpy as np

from mxnet.gluon.model_zoo.vision import get_model

batch_size = 1
image_shape = (3, 224, 224)
data_shape = (batch_size,) + image_shape
model_name = 'resnet18_v1' 

apivovarov

#!/usr/bin/env python3

import nnvm
import nnvm.testing
import tvm
import numpy as np

from mxnet.gluon.model_zoo.vision import get_model

batch_size = 1

apivovarov

curl --header "Content-Type: application/json" \
--request POST \
--data '{"url":"https://raw.githubusercontent.com/dmlc/mxnet.js/master/data/cat.png"}' \
https://gebtjgh3xg.execute-api.us-west-2.amazonaws.com/default/resnet50

apivovarov

#include <immintrin.h>
#include <stdio.h>
#include <stdint.h>	/* for uint64 definition */
#include <time.h>	/* for clock_gettime */
#include <string.h>     /* memset */

#define ARRAY_LENGTH 8 /* __m256 can handle vector of 8 32-bit floating-point values */
#define BILLION 1e9

/* Compile: gcc -mavx2 -O3 avx2-test.c -o avx2-test */

apivovarov

#!/usr/bin/env python3

import tensorflow as tf
import numpy as np
import time

from imagenet_preprocessing import preprocess_image
from imagenet1000 import imagenet_classes

ms = lambda: int(round(time.time() * 1000))

apivovarov

#!/usr/bin/env python3

import tensorflow as tf
import numpy as np
import time

from imagenet_preprocessing import preprocess_image
from imagenet1000 import imagenet_classes

ms = lambda: int(round(time.time() * 1000))