Hello to all,
I am new to eIQ, and I am trying to profile my own tensorflow model. I can import my model (.tflite or .h5). I checked that the different layers of the CNN were present, but when I launch the profiling, an error appears (see pictures). Unfortunately the error is not very explicit.
I get the same error as I profile the network:
- from a .tflite saved with the tensorflow library
- from a .h5 saved with the tensorflow library
- from a .tflite saved with eIQ from the loaded .h5
Does anyone have an idea where the error could be coming from?
Thanks in advance,
Hello David, thank you for your interest,
Here is a very minimal exemple :
step 1 in python :
input1 = tf.keras.layers.Input(shape=(1,1024,4))
x_conv_sep = tf.keras.layers.SeparableConv2D(4,
[1,3],
strides=(1, 1),
padding='same',
data_format="channels_last",
dilation_rate=(1,1),
depth_multiplier=2,
use_bias=False,
input_shape =[1,1024, 4],
depthwise_initializer='he_normal',
pointwise_initializer='truncated_normal',
name = "conv_dilatation",
)(input1)
model.save("conv2d_sep.h5")
step 2 in EIQ:
import model
Convert to tflite with quantization (int8) (see picture)
import tflite model
try to profile...
It seems to be the same as explain in the eIQ Toolkit User Guide 1.5.2 (sec. 4.1) but it doesn't work.
Do you see where is the problem ?
Thanks in advance,
Hadrien
