tflite_model_file = os.path.join(model_dir, model_name)
tflite_model_buf = open(tflite_model_file, "rb").read()
# Get TFLite model from buffer
try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
dtype = "float32"
width = 224
height = 224
image_data = load_test_image(dtype, width, height)
input_tensor = "input"
input_shape = (1, 224, 224, 3)
input_dtype = dtype
# Parse TFLite model and convert it to a Relay module
mod, params = relay.frontend.from_tflite(
tflite_model,
shape_dict={input_tensor: input_shape},
dtype_dict={input_tensor: input_dtype})
tvm_target = get_tvm_target(device, get_device_type(), get_device_arch(),
get_device_attributes())
tvm_targets = tvm.target.Target(tvm_target)
model_dir = download_model_zoo(model_dir, model_name)
tflite_model_file = os.path.join(model_dir, model_name)
tflite_model_buf = open(tflite_model_file, "rb").read()
# Get TFLite model from buffer
try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
dtype = "uint8"
image_data = load_test_image(dtype)
input_tensor = "input"
input_shape = (1, 224, 224, 3)
#input_dtype = "float32"
input_dtype = dtype
# Parse TFLite model and convert it to a Relay module
mod, params = relay.frontend.from_tflite(
tflite_model,
shape_dict={input_tensor: input_shape},
dtype_dict={input_tensor: input_dtype})
desired_layouts = {'qnn.conv2d': ['NCHW', 'default']}
seq = tvm.transform.Sequential([
relay.transform.RemoveUnusedFunctions(),
relay.transform.ConvertLayout(desired_layouts)
model_name = 'mobilenet_v1_1.0_224_quant.tflite'
repeat = 10
model_dir = download_model_zoo(model_dir, model_name)
tflite_model_file = os.path.join(model_dir, model_name)
tflite_model_buf = open(tflite_model_file, "rb").read()
try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
interpreter = Interpreter(tflite_model_file, num_threads=get_cpu_count())
interpreter.allocate_tensors()
_, height, width, _ = interpreter.get_input_details()[0]['shape']
image = load_test_image('uint8', height, width)
numpy_time = np.zeros(repeat)
for i in range(0, repeat):
start_time = time.time()
results = classify_image(interpreter, image)
elapsed_ms = (time.time() - start_time) * 1000
numpy_time[i] = elapsed_ms
print("tflite %-20s %-19s (%s)" % (model_name, "%.2f ms" % np.mean(numpy_time),
"%.2f ms" % np.std(numpy_time)))
model_name = 'inception_v3.tflite'
repeat = 10
model_dir = download_model_zoo(model_dir, model_name)
tflite_model_file = os.path.join(model_dir, model_name)
tflite_model_buf = open(tflite_model_file, "rb").read()
try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
interpreter = Interpreter(tflite_model_file, num_threads=get_cpu_count())
interpreter.allocate_tensors()
_, height, width, _ = interpreter.get_input_details()[0]['shape']
image = load_test_image('float32', height, width)
numpy_time = np.zeros(repeat)
for i in range(0, repeat):
start_time = time.time()
results = classify_image(interpreter, image)
elapsed_ms = (time.time() - start_time) * 1000
numpy_time[i] = elapsed_ms
print("tflite %-20s %-19s (%s)" % (model_name, "%.2f ms" % np.mean(numpy_time),
"%.2f ms" % np.std(numpy_time)))
model_dir = download_model_zoo(model_dir, model_name)
tflite_model_file = os.path.join(model_dir, model_name)
tflite_model_buf = open(tflite_model_file, "rb").read()
# Get TFLite model from buffer
try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
dtype = "float32"
image_data = load_test_image(dtype, 299, 299)
input_tensor = "input"
input_shape = (1, 299, 299, 3)
input_dtype = dtype
# Parse TFLite model and convert it to a Relay module
mod, params = relay.frontend.from_tflite(
tflite_model,
shape_dict={input_tensor: input_shape},
dtype_dict={input_tensor: input_dtype})
desired_layouts = {'nn.conv2d': ['NCHW', 'default']}
seq = tvm.transform.Sequential([
relay.transform.RemoveUnusedFunctions(),
relay.transform.ConvertLayout(desired_layouts)
])
model_dir = download_model_zoo(model_dir, model_name)
tflite_model_file = os.path.join(model_dir, model_name)
tflite_model_buf = open(tflite_model_file, "rb").read()
# Get TFLite model from buffer
try:
import tflite
tflite_model = tflite.Model.GetRootAsModel(tflite_model_buf, 0)
except AttributeError:
import tflite.Model
tflite_model = tflite.Model.Model.GetRootAsModel(tflite_model_buf, 0)
dtype="float32"
image_data = load_test_image(dtype, 416, 416)
input_tensor = "input_1"
input_shape = (1, 416, 416, 3)
input_dtype = dtype
# Parse TFLite model and convert it to a Relay module
mod, params = relay.frontend.from_tflite(tflite_model,
shape_dict={input_tensor: input_shape},
dtype_dict={input_tensor: input_dtype})
desired_layouts = {'nn.conv2d': ['NCHW', 'default']}
seq = tvm.transform.Sequential([relay.transform.RemoveUnusedFunctions(),relay.transform.ConvertLayout(desired_layouts)])
with tvm.transform.PassContext(opt_level=3):
mod = seq(mod)
