def test_nvprof(self):
if not fluid.core.is_compile_gpu():
return
epoc = 8
dshape = [4, 3, 28, 28]
data = layers.data(name='data', shape=[3, 28, 28], dtype='float32')
conv = layers.conv2d(data, 20, 3, stride=[1, 1], padding=[1, 1])
place = fluid.GPUPlace(0)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
with profiler.cuda_profiler("cuda_profiler.txt", 'csv') as nvprof:
for i in range(epoc):
input = np.random.random(dshape).astype('float32')
exe.run(fluid.default_main_program(), feed={'data': input})
map(lambda x: x[0].reshape([1, 28, 28]), data)).astype(DTYPE)
y_data = np.array(map(lambda x: x[1], data)).astype("int64")
y_data = y_data.reshape([len(y_data), 1])
start = time.clock()
outs = exe.run(fluid.default_main_program(),
feed={"pixel": img_data,
"label": y_data},
fetch_list=[avg_cost] + accuracy.metrics)
end = time.clock()
loss = np.array(outs[0])
acc = np.array(outs[1])
print("pass=%d, batch=%d, loss=%f, error=%f, elapse=%f" %
(pass_id, batch_id, loss, 1 - acc, (end - start) / 1000))
pass_end = time.clock()
test_avg_acc = eval_test(exe, accuracy, avg_cost)
pass_acc = accuracy.eval(exe)
print("pass=%d, test_avg_acc=%f, test_avg_acc=%f, elapse=%f" %
(pass_id, pass_acc, test_avg_acc, (pass_end - pass_start) / 1000))
if __name__ == '__main__':
args = parse_args()
print_arguments(args)
if args.use_nvprof and args.device == 'GPU':
with profiler.cuda_profiler("cuda_profiler.txt", 'csv') as nvprof:
run_benchmark(cnn_model, args)
else:
run_benchmark(cnn_model, args)
