Comments (3)
rshih32
commented on June 3, 2024
1
Hi,
The error
Either (1) select a slice where the `to_cut` corresponds to a single tensor, or (2) implement/use a `QoI` object that supports lists of tensors, i.e., where the parameter, `x`, to `__call__` is expected/allowed to be a list of 3 tensors.
implies that your model has 3 output tensors. In order to deal with this, you will need to use the DoI/QoI framework.
generally you need to be able to run gradients w.r.t. some output dy/dx. where y should be a scalar. (usually you do something like max(softmax) for multiclass.
try:
from trulens.nn.attribution import InternalInfluence
from trulens.nn.distributions import LinearDoi
from trulens.nn.quantities import QoI
from trulens.nn.slices import Cut, InputCut, OutputCut, Slice
class MyQoI(QoI):
def def __init__(self,*args):
"""
save anything you need
"""
def __call__(self, y: TensorLike) -> TensorLike:
# y is your output tensors, you can add debug statements here to see what is coming here.
# I assume you have 3 tensors here so here is some pseudocode -
return tf.max_idx(tf.softmax(y[idx_of_tensor_that_represents yhat output))
yolo = Load_Yolo_model() # yolo is <class 'tensorflow.python.keras.engine.functional.Functional'> object
model_wrapped = get_model_wrapper(yolo)
# The LinearDoi is equivalent to using integratedgradients
my_ig = InternalInfluence(model,
Slice(InputCut(), OutputCut()),
MyQoI(),
LinearDoi(resolution=20))
with PIL.Image.open(image_path).convert('RGB') as img:
x = np.array(img.resize((416, 416)))
x_np = np.array(img.resize((416, 416), PIL.Image.ANTIALIAS))[np.newaxis]
input_attributions = my_ig.attributions(x_np)
from trulens.
rshih32
commented on June 3, 2024
1
you could also replace the OutputCut in Slice with Cut(layer_name) where layer_name can come from model.summary()
The QoI call will get the output of that layer.
example:
my_ig = InternalInfluence(model,
Slice(InputCut(), Cut('tf.math.sigmoid_8')),
MyQoI(),
LinearDoi(resolution=20))
from trulens.
Guanzhao-hub
commented on June 3, 2024
I'm using TensorFlow 2.5 and here is the output of my trained model. Any help would be appreciated!
My network summary from yolo.summary() is:
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 416, 416, 3) 0
__________________________________________________________________________________________________
conv2d (Conv2D) (None, 416, 416, 32) 864 input_1[0][0]
__________________________________________________________________________________________________
batch_normalization (BatchNorma (None, 416, 416, 32) 128 conv2d[0][0]
__________________________________________________________________________________________________
leaky_re_lu (LeakyReLU) (None, 416, 416, 32) 0 batch_normalization[0][0]
__________________________________________________________________________________________________
zero_padding2d (ZeroPadding2D) (None, 417, 417, 32) 0 leaky_re_lu[0][0]
__________________________________________________________________________________________________
conv2d_1 (Conv2D) (None, 208, 208, 64) 18432 zero_padding2d[0][0]
__________________________________________________________________________________________________
batch_normalization_1 (BatchNor (None, 208, 208, 64) 256 conv2d_1[0][0]
__________________________________________________________________________________________________
leaky_re_lu_1 (LeakyReLU) (None, 208, 208, 64) 0 batch_normalization_1[0][0]
__________________________________________________________________________________________________
conv2d_2 (Conv2D) (None, 208, 208, 32) 2048 leaky_re_lu_1[0][0]
__________________________________________________________________________________________________
batch_normalization_2 (BatchNor (None, 208, 208, 32) 128 conv2d_2[0][0]
__________________________________________________________________________________________________
leaky_re_lu_2 (LeakyReLU) (None, 208, 208, 32) 0 batch_normalization_2[0][0]
__________________________________________________________________________________________________
conv2d_3 (Conv2D) (None, 208, 208, 64) 18432 leaky_re_lu_2[0][0]
__________________________________________________________________________________________________
batch_normalization_3 (BatchNor (None, 208, 208, 64) 256 conv2d_3[0][0]
__________________________________________________________________________________________________
leaky_re_lu_3 (LeakyReLU) (None, 208, 208, 64) 0 batch_normalization_3[0][0]
__________________________________________________________________________________________________
tf.__operators__.add (TFOpLambd (None, 208, 208, 64) 0 leaky_re_lu_1[0][0]
leaky_re_lu_3[0][0]
__________________________________________________________________________________________________
zero_padding2d_1 (ZeroPadding2D (None, 209, 209, 64) 0 tf.__operators__.add[0][0]
__________________________________________________________________________________________________
conv2d_4 (Conv2D) (None, 104, 104, 128 73728 zero_padding2d_1[0][0]
__________________________________________________________________________________________________
batch_normalization_4 (BatchNor (None, 104, 104, 128 512 conv2d_4[0][0]
__________________________________________________________________________________________________
leaky_re_lu_4 (LeakyReLU) (None, 104, 104, 128 0 batch_normalization_4[0][0]
__________________________________________________________________________________________________
conv2d_5 (Conv2D) (None, 104, 104, 64) 8192 leaky_re_lu_4[0][0]
__________________________________________________________________________________________________
batch_normalization_5 (BatchNor (None, 104, 104, 64) 256 conv2d_5[0][0]
__________________________________________________________________________________________________
leaky_re_lu_5 (LeakyReLU) (None, 104, 104, 64) 0 batch_normalization_5[0][0]
__________________________________________________________________________________________________
conv2d_6 (Conv2D) (None, 104, 104, 128 73728 leaky_re_lu_5[0][0]
__________________________________________________________________________________________________
batch_normalization_6 (BatchNor (None, 104, 104, 128 512 conv2d_6[0][0]
__________________________________________________________________________________________________
leaky_re_lu_6 (LeakyReLU) (None, 104, 104, 128 0 batch_normalization_6[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_1 (TFOpLam (None, 104, 104, 128 0 leaky_re_lu_4[0][0]
leaky_re_lu_6[0][0]
__________________________________________________________________________________________________
conv2d_7 (Conv2D) (None, 104, 104, 64) 8192 tf.__operators__.add_1[0][0]
__________________________________________________________________________________________________
batch_normalization_7 (BatchNor (None, 104, 104, 64) 256 conv2d_7[0][0]
__________________________________________________________________________________________________
leaky_re_lu_7 (LeakyReLU) (None, 104, 104, 64) 0 batch_normalization_7[0][0]
__________________________________________________________________________________________________
conv2d_8 (Conv2D) (None, 104, 104, 128 73728 leaky_re_lu_7[0][0]
__________________________________________________________________________________________________
batch_normalization_8 (BatchNor (None, 104, 104, 128 512 conv2d_8[0][0]
__________________________________________________________________________________________________
leaky_re_lu_8 (LeakyReLU) (None, 104, 104, 128 0 batch_normalization_8[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_2 (TFOpLam (None, 104, 104, 128 0 tf.__operators__.add_1[0][0]
leaky_re_lu_8[0][0]
__________________________________________________________________________________________________
zero_padding2d_2 (ZeroPadding2D (None, 105, 105, 128 0 tf.__operators__.add_2[0][0]
__________________________________________________________________________________________________
conv2d_9 (Conv2D) (None, 52, 52, 256) 294912 zero_padding2d_2[0][0]
__________________________________________________________________________________________________
batch_normalization_9 (BatchNor (None, 52, 52, 256) 1024 conv2d_9[0][0]
__________________________________________________________________________________________________
leaky_re_lu_9 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_9[0][0]
__________________________________________________________________________________________________
conv2d_10 (Conv2D) (None, 52, 52, 128) 32768 leaky_re_lu_9[0][0]
__________________________________________________________________________________________________
batch_normalization_10 (BatchNo (None, 52, 52, 128) 512 conv2d_10[0][0]
__________________________________________________________________________________________________
leaky_re_lu_10 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_10[0][0]
__________________________________________________________________________________________________
conv2d_11 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_10[0][0]
__________________________________________________________________________________________________
batch_normalization_11 (BatchNo (None, 52, 52, 256) 1024 conv2d_11[0][0]
__________________________________________________________________________________________________
leaky_re_lu_11 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_11[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_3 (TFOpLam (None, 52, 52, 256) 0 leaky_re_lu_9[0][0]
leaky_re_lu_11[0][0]
__________________________________________________________________________________________________
conv2d_12 (Conv2D) (None, 52, 52, 128) 32768 tf.__operators__.add_3[0][0]
__________________________________________________________________________________________________
batch_normalization_12 (BatchNo (None, 52, 52, 128) 512 conv2d_12[0][0]
__________________________________________________________________________________________________
leaky_re_lu_12 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_12[0][0]
__________________________________________________________________________________________________
conv2d_13 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_12[0][0]
__________________________________________________________________________________________________
batch_normalization_13 (BatchNo (None, 52, 52, 256) 1024 conv2d_13[0][0]
__________________________________________________________________________________________________
leaky_re_lu_13 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_13[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_4 (TFOpLam (None, 52, 52, 256) 0 tf.__operators__.add_3[0][0]
leaky_re_lu_13[0][0]
__________________________________________________________________________________________________
conv2d_14 (Conv2D) (None, 52, 52, 128) 32768 tf.__operators__.add_4[0][0]
__________________________________________________________________________________________________
batch_normalization_14 (BatchNo (None, 52, 52, 128) 512 conv2d_14[0][0]
__________________________________________________________________________________________________
leaky_re_lu_14 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_14[0][0]
__________________________________________________________________________________________________
conv2d_15 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_14[0][0]
__________________________________________________________________________________________________
batch_normalization_15 (BatchNo (None, 52, 52, 256) 1024 conv2d_15[0][0]
__________________________________________________________________________________________________
leaky_re_lu_15 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_15[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_5 (TFOpLam (None, 52, 52, 256) 0 tf.__operators__.add_4[0][0]
leaky_re_lu_15[0][0]
__________________________________________________________________________________________________
conv2d_16 (Conv2D) (None, 52, 52, 128) 32768 tf.__operators__.add_5[0][0]
__________________________________________________________________________________________________
batch_normalization_16 (BatchNo (None, 52, 52, 128) 512 conv2d_16[0][0]
__________________________________________________________________________________________________
leaky_re_lu_16 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_16[0][0]
__________________________________________________________________________________________________
conv2d_17 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_16[0][0]
__________________________________________________________________________________________________
batch_normalization_17 (BatchNo (None, 52, 52, 256) 1024 conv2d_17[0][0]
__________________________________________________________________________________________________
leaky_re_lu_17 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_17[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_6 (TFOpLam (None, 52, 52, 256) 0 tf.__operators__.add_5[0][0]
leaky_re_lu_17[0][0]
__________________________________________________________________________________________________
conv2d_18 (Conv2D) (None, 52, 52, 128) 32768 tf.__operators__.add_6[0][0]
__________________________________________________________________________________________________
batch_normalization_18 (BatchNo (None, 52, 52, 128) 512 conv2d_18[0][0]
__________________________________________________________________________________________________
leaky_re_lu_18 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_18[0][0]
__________________________________________________________________________________________________
conv2d_19 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_18[0][0]
__________________________________________________________________________________________________
batch_normalization_19 (BatchNo (None, 52, 52, 256) 1024 conv2d_19[0][0]
__________________________________________________________________________________________________
leaky_re_lu_19 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_19[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_7 (TFOpLam (None, 52, 52, 256) 0 tf.__operators__.add_6[0][0]
leaky_re_lu_19[0][0]
__________________________________________________________________________________________________
conv2d_20 (Conv2D) (None, 52, 52, 128) 32768 tf.__operators__.add_7[0][0]
__________________________________________________________________________________________________
batch_normalization_20 (BatchNo (None, 52, 52, 128) 512 conv2d_20[0][0]
__________________________________________________________________________________________________
leaky_re_lu_20 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_20[0][0]
__________________________________________________________________________________________________
conv2d_21 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_20[0][0]
__________________________________________________________________________________________________
batch_normalization_21 (BatchNo (None, 52, 52, 256) 1024 conv2d_21[0][0]
__________________________________________________________________________________________________
leaky_re_lu_21 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_21[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_8 (TFOpLam (None, 52, 52, 256) 0 tf.__operators__.add_7[0][0]
leaky_re_lu_21[0][0]
__________________________________________________________________________________________________
conv2d_22 (Conv2D) (None, 52, 52, 128) 32768 tf.__operators__.add_8[0][0]
__________________________________________________________________________________________________
batch_normalization_22 (BatchNo (None, 52, 52, 128) 512 conv2d_22[0][0]
__________________________________________________________________________________________________
leaky_re_lu_22 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_22[0][0]
__________________________________________________________________________________________________
conv2d_23 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_22[0][0]
__________________________________________________________________________________________________
batch_normalization_23 (BatchNo (None, 52, 52, 256) 1024 conv2d_23[0][0]
__________________________________________________________________________________________________
leaky_re_lu_23 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_23[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_9 (TFOpLam (None, 52, 52, 256) 0 tf.__operators__.add_8[0][0]
leaky_re_lu_23[0][0]
__________________________________________________________________________________________________
conv2d_24 (Conv2D) (None, 52, 52, 128) 32768 tf.__operators__.add_9[0][0]
__________________________________________________________________________________________________
batch_normalization_24 (BatchNo (None, 52, 52, 128) 512 conv2d_24[0][0]
__________________________________________________________________________________________________
leaky_re_lu_24 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_24[0][0]
__________________________________________________________________________________________________
conv2d_25 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_24[0][0]
__________________________________________________________________________________________________
batch_normalization_25 (BatchNo (None, 52, 52, 256) 1024 conv2d_25[0][0]
__________________________________________________________________________________________________
leaky_re_lu_25 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_25[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_10 (TFOpLa (None, 52, 52, 256) 0 tf.__operators__.add_9[0][0]
leaky_re_lu_25[0][0]
__________________________________________________________________________________________________
zero_padding2d_3 (ZeroPadding2D (None, 53, 53, 256) 0 tf.__operators__.add_10[0][0]
__________________________________________________________________________________________________
conv2d_26 (Conv2D) (None, 26, 26, 512) 1179648 zero_padding2d_3[0][0]
__________________________________________________________________________________________________
batch_normalization_26 (BatchNo (None, 26, 26, 512) 2048 conv2d_26[0][0]
__________________________________________________________________________________________________
leaky_re_lu_26 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_26[0][0]
__________________________________________________________________________________________________
conv2d_27 (Conv2D) (None, 26, 26, 256) 131072 leaky_re_lu_26[0][0]
__________________________________________________________________________________________________
batch_normalization_27 (BatchNo (None, 26, 26, 256) 1024 conv2d_27[0][0]
__________________________________________________________________________________________________
leaky_re_lu_27 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_27[0][0]
__________________________________________________________________________________________________
conv2d_28 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_27[0][0]
__________________________________________________________________________________________________
batch_normalization_28 (BatchNo (None, 26, 26, 512) 2048 conv2d_28[0][0]
__________________________________________________________________________________________________
leaky_re_lu_28 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_28[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_11 (TFOpLa (None, 26, 26, 512) 0 leaky_re_lu_26[0][0]
leaky_re_lu_28[0][0]
__________________________________________________________________________________________________
conv2d_29 (Conv2D) (None, 26, 26, 256) 131072 tf.__operators__.add_11[0][0]
__________________________________________________________________________________________________
batch_normalization_29 (BatchNo (None, 26, 26, 256) 1024 conv2d_29[0][0]
__________________________________________________________________________________________________
leaky_re_lu_29 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_29[0][0]
__________________________________________________________________________________________________
conv2d_30 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_29[0][0]
__________________________________________________________________________________________________
batch_normalization_30 (BatchNo (None, 26, 26, 512) 2048 conv2d_30[0][0]
__________________________________________________________________________________________________
leaky_re_lu_30 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_30[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_12 (TFOpLa (None, 26, 26, 512) 0 tf.__operators__.add_11[0][0]
leaky_re_lu_30[0][0]
__________________________________________________________________________________________________
conv2d_31 (Conv2D) (None, 26, 26, 256) 131072 tf.__operators__.add_12[0][0]
__________________________________________________________________________________________________
batch_normalization_31 (BatchNo (None, 26, 26, 256) 1024 conv2d_31[0][0]
__________________________________________________________________________________________________
leaky_re_lu_31 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_31[0][0]
__________________________________________________________________________________________________
conv2d_32 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_31[0][0]
__________________________________________________________________________________________________
batch_normalization_32 (BatchNo (None, 26, 26, 512) 2048 conv2d_32[0][0]
__________________________________________________________________________________________________
leaky_re_lu_32 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_32[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_13 (TFOpLa (None, 26, 26, 512) 0 tf.__operators__.add_12[0][0]
leaky_re_lu_32[0][0]
__________________________________________________________________________________________________
conv2d_33 (Conv2D) (None, 26, 26, 256) 131072 tf.__operators__.add_13[0][0]
__________________________________________________________________________________________________
batch_normalization_33 (BatchNo (None, 26, 26, 256) 1024 conv2d_33[0][0]
__________________________________________________________________________________________________
leaky_re_lu_33 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_33[0][0]
__________________________________________________________________________________________________
conv2d_34 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_33[0][0]
__________________________________________________________________________________________________
batch_normalization_34 (BatchNo (None, 26, 26, 512) 2048 conv2d_34[0][0]
__________________________________________________________________________________________________
leaky_re_lu_34 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_34[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_14 (TFOpLa (None, 26, 26, 512) 0 tf.__operators__.add_13[0][0]
leaky_re_lu_34[0][0]
__________________________________________________________________________________________________
conv2d_35 (Conv2D) (None, 26, 26, 256) 131072 tf.__operators__.add_14[0][0]
__________________________________________________________________________________________________
batch_normalization_35 (BatchNo (None, 26, 26, 256) 1024 conv2d_35[0][0]
__________________________________________________________________________________________________
leaky_re_lu_35 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_35[0][0]
__________________________________________________________________________________________________
conv2d_36 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_35[0][0]
__________________________________________________________________________________________________
batch_normalization_36 (BatchNo (None, 26, 26, 512) 2048 conv2d_36[0][0]
__________________________________________________________________________________________________
leaky_re_lu_36 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_36[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_15 (TFOpLa (None, 26, 26, 512) 0 tf.__operators__.add_14[0][0]
leaky_re_lu_36[0][0]
__________________________________________________________________________________________________
conv2d_37 (Conv2D) (None, 26, 26, 256) 131072 tf.__operators__.add_15[0][0]
__________________________________________________________________________________________________
batch_normalization_37 (BatchNo (None, 26, 26, 256) 1024 conv2d_37[0][0]
__________________________________________________________________________________________________
leaky_re_lu_37 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_37[0][0]
__________________________________________________________________________________________________
conv2d_38 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_37[0][0]
__________________________________________________________________________________________________
batch_normalization_38 (BatchNo (None, 26, 26, 512) 2048 conv2d_38[0][0]
__________________________________________________________________________________________________
leaky_re_lu_38 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_38[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_16 (TFOpLa (None, 26, 26, 512) 0 tf.__operators__.add_15[0][0]
leaky_re_lu_38[0][0]
__________________________________________________________________________________________________
conv2d_39 (Conv2D) (None, 26, 26, 256) 131072 tf.__operators__.add_16[0][0]
__________________________________________________________________________________________________
batch_normalization_39 (BatchNo (None, 26, 26, 256) 1024 conv2d_39[0][0]
__________________________________________________________________________________________________
leaky_re_lu_39 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_39[0][0]
__________________________________________________________________________________________________
conv2d_40 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_39[0][0]
__________________________________________________________________________________________________
batch_normalization_40 (BatchNo (None, 26, 26, 512) 2048 conv2d_40[0][0]
__________________________________________________________________________________________________
leaky_re_lu_40 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_40[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_17 (TFOpLa (None, 26, 26, 512) 0 tf.__operators__.add_16[0][0]
leaky_re_lu_40[0][0]
__________________________________________________________________________________________________
conv2d_41 (Conv2D) (None, 26, 26, 256) 131072 tf.__operators__.add_17[0][0]
__________________________________________________________________________________________________
batch_normalization_41 (BatchNo (None, 26, 26, 256) 1024 conv2d_41[0][0]
__________________________________________________________________________________________________
leaky_re_lu_41 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_41[0][0]
__________________________________________________________________________________________________
conv2d_42 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_41[0][0]
__________________________________________________________________________________________________
batch_normalization_42 (BatchNo (None, 26, 26, 512) 2048 conv2d_42[0][0]
__________________________________________________________________________________________________
leaky_re_lu_42 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_42[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_18 (TFOpLa (None, 26, 26, 512) 0 tf.__operators__.add_17[0][0]
leaky_re_lu_42[0][0]
__________________________________________________________________________________________________
zero_padding2d_4 (ZeroPadding2D (None, 27, 27, 512) 0 tf.__operators__.add_18[0][0]
__________________________________________________________________________________________________
conv2d_43 (Conv2D) (None, 13, 13, 1024) 4718592 zero_padding2d_4[0][0]
__________________________________________________________________________________________________
batch_normalization_43 (BatchNo (None, 13, 13, 1024) 4096 conv2d_43[0][0]
__________________________________________________________________________________________________
leaky_re_lu_43 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_43[0][0]
__________________________________________________________________________________________________
conv2d_44 (Conv2D) (None, 13, 13, 512) 524288 leaky_re_lu_43[0][0]
__________________________________________________________________________________________________
batch_normalization_44 (BatchNo (None, 13, 13, 512) 2048 conv2d_44[0][0]
__________________________________________________________________________________________________
leaky_re_lu_44 (LeakyReLU) (None, 13, 13, 512) 0 batch_normalization_44[0][0]
__________________________________________________________________________________________________
conv2d_45 (Conv2D) (None, 13, 13, 1024) 4718592 leaky_re_lu_44[0][0]
__________________________________________________________________________________________________
batch_normalization_45 (BatchNo (None, 13, 13, 1024) 4096 conv2d_45[0][0]
__________________________________________________________________________________________________
leaky_re_lu_45 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_45[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_19 (TFOpLa (None, 13, 13, 1024) 0 leaky_re_lu_43[0][0]
leaky_re_lu_45[0][0]
__________________________________________________________________________________________________
conv2d_46 (Conv2D) (None, 13, 13, 512) 524288 tf.__operators__.add_19[0][0]
__________________________________________________________________________________________________
batch_normalization_46 (BatchNo (None, 13, 13, 512) 2048 conv2d_46[0][0]
__________________________________________________________________________________________________
leaky_re_lu_46 (LeakyReLU) (None, 13, 13, 512) 0 batch_normalization_46[0][0]
__________________________________________________________________________________________________
conv2d_47 (Conv2D) (None, 13, 13, 1024) 4718592 leaky_re_lu_46[0][0]
__________________________________________________________________________________________________
batch_normalization_47 (BatchNo (None, 13, 13, 1024) 4096 conv2d_47[0][0]
__________________________________________________________________________________________________
leaky_re_lu_47 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_47[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_20 (TFOpLa (None, 13, 13, 1024) 0 tf.__operators__.add_19[0][0]
leaky_re_lu_47[0][0]
__________________________________________________________________________________________________
conv2d_48 (Conv2D) (None, 13, 13, 512) 524288 tf.__operators__.add_20[0][0]
__________________________________________________________________________________________________
batch_normalization_48 (BatchNo (None, 13, 13, 512) 2048 conv2d_48[0][0]
__________________________________________________________________________________________________
leaky_re_lu_48 (LeakyReLU) (None, 13, 13, 512) 0 batch_normalization_48[0][0]
__________________________________________________________________________________________________
conv2d_49 (Conv2D) (None, 13, 13, 1024) 4718592 leaky_re_lu_48[0][0]
__________________________________________________________________________________________________
batch_normalization_49 (BatchNo (None, 13, 13, 1024) 4096 conv2d_49[0][0]
__________________________________________________________________________________________________
leaky_re_lu_49 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_49[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_21 (TFOpLa (None, 13, 13, 1024) 0 tf.__operators__.add_20[0][0]
leaky_re_lu_49[0][0]
__________________________________________________________________________________________________
conv2d_50 (Conv2D) (None, 13, 13, 512) 524288 tf.__operators__.add_21[0][0]
__________________________________________________________________________________________________
batch_normalization_50 (BatchNo (None, 13, 13, 512) 2048 conv2d_50[0][0]
__________________________________________________________________________________________________
leaky_re_lu_50 (LeakyReLU) (None, 13, 13, 512) 0 batch_normalization_50[0][0]
__________________________________________________________________________________________________
conv2d_51 (Conv2D) (None, 13, 13, 1024) 4718592 leaky_re_lu_50[0][0]
__________________________________________________________________________________________________
batch_normalization_51 (BatchNo (None, 13, 13, 1024) 4096 conv2d_51[0][0]
__________________________________________________________________________________________________
leaky_re_lu_51 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_51[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_22 (TFOpLa (None, 13, 13, 1024) 0 tf.__operators__.add_21[0][0]
leaky_re_lu_51[0][0]
__________________________________________________________________________________________________
conv2d_52 (Conv2D) (None, 13, 13, 512) 524288 tf.__operators__.add_22[0][0]
__________________________________________________________________________________________________
batch_normalization_52 (BatchNo (None, 13, 13, 512) 2048 conv2d_52[0][0]
__________________________________________________________________________________________________
leaky_re_lu_52 (LeakyReLU) (None, 13, 13, 512) 0 batch_normalization_52[0][0]
__________________________________________________________________________________________________
conv2d_53 (Conv2D) (None, 13, 13, 1024) 4718592 leaky_re_lu_52[0][0]
__________________________________________________________________________________________________
batch_normalization_53 (BatchNo (None, 13, 13, 1024) 4096 conv2d_53[0][0]
__________________________________________________________________________________________________
leaky_re_lu_53 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_53[0][0]
__________________________________________________________________________________________________
conv2d_54 (Conv2D) (None, 13, 13, 512) 524288 leaky_re_lu_53[0][0]
__________________________________________________________________________________________________
batch_normalization_54 (BatchNo (None, 13, 13, 512) 2048 conv2d_54[0][0]
__________________________________________________________________________________________________
leaky_re_lu_54 (LeakyReLU) (None, 13, 13, 512) 0 batch_normalization_54[0][0]
__________________________________________________________________________________________________
conv2d_55 (Conv2D) (None, 13, 13, 1024) 4718592 leaky_re_lu_54[0][0]
__________________________________________________________________________________________________
batch_normalization_55 (BatchNo (None, 13, 13, 1024) 4096 conv2d_55[0][0]
__________________________________________________________________________________________________
leaky_re_lu_55 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_55[0][0]
__________________________________________________________________________________________________
conv2d_56 (Conv2D) (None, 13, 13, 512) 524288 leaky_re_lu_55[0][0]
__________________________________________________________________________________________________
batch_normalization_56 (BatchNo (None, 13, 13, 512) 2048 conv2d_56[0][0]
__________________________________________________________________________________________________
leaky_re_lu_56 (LeakyReLU) (None, 13, 13, 512) 0 batch_normalization_56[0][0]
__________________________________________________________________________________________________
conv2d_59 (Conv2D) (None, 13, 13, 256) 131072 leaky_re_lu_56[0][0]
__________________________________________________________________________________________________
batch_normalization_58 (BatchNo (None, 13, 13, 256) 1024 conv2d_59[0][0]
__________________________________________________________________________________________________
leaky_re_lu_58 (LeakyReLU) (None, 13, 13, 256) 0 batch_normalization_58[0][0]
__________________________________________________________________________________________________
tf.image.resize (TFOpLambda) (None, 26, 26, 256) 0 leaky_re_lu_58[0][0]
__________________________________________________________________________________________________
tf.concat (TFOpLambda) (None, 26, 26, 768) 0 tf.image.resize[0][0]
tf.__operators__.add_18[0][0]
__________________________________________________________________________________________________
conv2d_60 (Conv2D) (None, 26, 26, 256) 196608 tf.concat[0][0]
__________________________________________________________________________________________________
batch_normalization_59 (BatchNo (None, 26, 26, 256) 1024 conv2d_60[0][0]
__________________________________________________________________________________________________
leaky_re_lu_59 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_59[0][0]
__________________________________________________________________________________________________
conv2d_61 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_59[0][0]
__________________________________________________________________________________________________
batch_normalization_60 (BatchNo (None, 26, 26, 512) 2048 conv2d_61[0][0]
__________________________________________________________________________________________________
leaky_re_lu_60 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_60[0][0]
__________________________________________________________________________________________________
conv2d_62 (Conv2D) (None, 26, 26, 256) 131072 leaky_re_lu_60[0][0]
__________________________________________________________________________________________________
batch_normalization_61 (BatchNo (None, 26, 26, 256) 1024 conv2d_62[0][0]
__________________________________________________________________________________________________
leaky_re_lu_61 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_61[0][0]
__________________________________________________________________________________________________
conv2d_63 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_61[0][0]
__________________________________________________________________________________________________
batch_normalization_62 (BatchNo (None, 26, 26, 512) 2048 conv2d_63[0][0]
__________________________________________________________________________________________________
leaky_re_lu_62 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_62[0][0]
__________________________________________________________________________________________________
conv2d_64 (Conv2D) (None, 26, 26, 256) 131072 leaky_re_lu_62[0][0]
__________________________________________________________________________________________________
batch_normalization_63 (BatchNo (None, 26, 26, 256) 1024 conv2d_64[0][0]
__________________________________________________________________________________________________
leaky_re_lu_63 (LeakyReLU) (None, 26, 26, 256) 0 batch_normalization_63[0][0]
__________________________________________________________________________________________________
conv2d_67 (Conv2D) (None, 26, 26, 128) 32768 leaky_re_lu_63[0][0]
__________________________________________________________________________________________________
batch_normalization_65 (BatchNo (None, 26, 26, 128) 512 conv2d_67[0][0]
__________________________________________________________________________________________________
leaky_re_lu_65 (LeakyReLU) (None, 26, 26, 128) 0 batch_normalization_65[0][0]
__________________________________________________________________________________________________
tf.image.resize_1 (TFOpLambda) (None, 52, 52, 128) 0 leaky_re_lu_65[0][0]
__________________________________________________________________________________________________
tf.concat_1 (TFOpLambda) (None, 52, 52, 384) 0 tf.image.resize_1[0][0]
tf.__operators__.add_10[0][0]
__________________________________________________________________________________________________
conv2d_68 (Conv2D) (None, 52, 52, 128) 49152 tf.concat_1[0][0]
__________________________________________________________________________________________________
batch_normalization_66 (BatchNo (None, 52, 52, 128) 512 conv2d_68[0][0]
__________________________________________________________________________________________________
leaky_re_lu_66 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_66[0][0]
__________________________________________________________________________________________________
conv2d_69 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_66[0][0]
__________________________________________________________________________________________________
batch_normalization_67 (BatchNo (None, 52, 52, 256) 1024 conv2d_69[0][0]
__________________________________________________________________________________________________
leaky_re_lu_67 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_67[0][0]
__________________________________________________________________________________________________
conv2d_70 (Conv2D) (None, 52, 52, 128) 32768 leaky_re_lu_67[0][0]
__________________________________________________________________________________________________
batch_normalization_68 (BatchNo (None, 52, 52, 128) 512 conv2d_70[0][0]
__________________________________________________________________________________________________
leaky_re_lu_68 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_68[0][0]
__________________________________________________________________________________________________
conv2d_71 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_68[0][0]
__________________________________________________________________________________________________
batch_normalization_69 (BatchNo (None, 52, 52, 256) 1024 conv2d_71[0][0]
__________________________________________________________________________________________________
leaky_re_lu_69 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_69[0][0]
__________________________________________________________________________________________________
conv2d_72 (Conv2D) (None, 52, 52, 128) 32768 leaky_re_lu_69[0][0]
__________________________________________________________________________________________________
batch_normalization_70 (BatchNo (None, 52, 52, 128) 512 conv2d_72[0][0]
__________________________________________________________________________________________________
leaky_re_lu_70 (LeakyReLU) (None, 52, 52, 128) 0 batch_normalization_70[0][0]
__________________________________________________________________________________________________
conv2d_73 (Conv2D) (None, 52, 52, 256) 294912 leaky_re_lu_70[0][0]
__________________________________________________________________________________________________
conv2d_65 (Conv2D) (None, 26, 26, 512) 1179648 leaky_re_lu_63[0][0]
__________________________________________________________________________________________________
conv2d_57 (Conv2D) (None, 13, 13, 1024) 4718592 leaky_re_lu_56[0][0]
__________________________________________________________________________________________________
batch_normalization_71 (BatchNo (None, 52, 52, 256) 1024 conv2d_73[0][0]
__________________________________________________________________________________________________
batch_normalization_64 (BatchNo (None, 26, 26, 512) 2048 conv2d_65[0][0]
__________________________________________________________________________________________________
batch_normalization_57 (BatchNo (None, 13, 13, 1024) 4096 conv2d_57[0][0]
__________________________________________________________________________________________________
leaky_re_lu_71 (LeakyReLU) (None, 52, 52, 256) 0 batch_normalization_71[0][0]
__________________________________________________________________________________________________
leaky_re_lu_64 (LeakyReLU) (None, 26, 26, 512) 0 batch_normalization_64[0][0]
__________________________________________________________________________________________________
leaky_re_lu_57 (LeakyReLU) (None, 13, 13, 1024) 0 batch_normalization_57[0][0]
__________________________________________________________________________________________________
conv2d_74 (Conv2D) (None, 52, 52, 18) 4626 leaky_re_lu_71[0][0]
__________________________________________________________________________________________________
conv2d_66 (Conv2D) (None, 26, 26, 18) 9234 leaky_re_lu_64[0][0]
__________________________________________________________________________________________________
conv2d_58 (Conv2D) (None, 13, 13, 18) 18450 leaky_re_lu_57[0][0]
__________________________________________________________________________________________________
tf.compat.v1.shape (TFOpLambda) (4,) 0 conv2d_74[0][0]
__________________________________________________________________________________________________
tf.compat.v1.shape_1 (TFOpLambd (4,) 0 conv2d_66[0][0]
__________________________________________________________________________________________________
tf.compat.v1.shape_2 (TFOpLambd (4,) 0 conv2d_58[0][0]
__________________________________________________________________________________________________
tf.__operators__.getitem_1 (Sli () 0 tf.compat.v1.shape[0][0]
__________________________________________________________________________________________________
tf.__operators__.getitem_5 (Sli () 0 tf.compat.v1.shape_1[0][0]
__________________________________________________________________________________________________
tf.__operators__.getitem_9 (Sli () 0 tf.compat.v1.shape_2[0][0]
__________________________________________________________________________________________________
tf.range (TFOpLambda) (None,) 0 tf.__operators__.getitem_1[0][0]
__________________________________________________________________________________________________
tf.range_1 (TFOpLambda) (None,) 0 tf.__operators__.getitem_1[0][0]
__________________________________________________________________________________________________
tf.range_2 (TFOpLambda) (None,) 0 tf.__operators__.getitem_5[0][0]
__________________________________________________________________________________________________
tf.range_3 (TFOpLambda) (None,) 0 tf.__operators__.getitem_5[0][0]
__________________________________________________________________________________________________
tf.range_4 (TFOpLambda) (None,) 0 tf.__operators__.getitem_9[0][0]
__________________________________________________________________________________________________
tf.range_5 (TFOpLambda) (None,) 0 tf.__operators__.getitem_9[0][0]
__________________________________________________________________________________________________
tf.meshgrid (TFOpLambda) [(None, None), (None 0 tf.range[0][0]
tf.range_1[0][0]
__________________________________________________________________________________________________
tf.meshgrid_1 (TFOpLambda) [(None, None), (None 0 tf.range_2[0][0]
tf.range_3[0][0]
__________________________________________________________________________________________________
tf.meshgrid_2 (TFOpLambda) [(None, None), (None 0 tf.range_4[0][0]
tf.range_5[0][0]
__________________________________________________________________________________________________
tf.stack_2 (TFOpLambda) (None, None, 2) 0 tf.meshgrid[0][0]
tf.meshgrid[0][1]
__________________________________________________________________________________________________
tf.stack_5 (TFOpLambda) (None, None, 2) 0 tf.meshgrid_1[0][0]
tf.meshgrid_1[0][1]
__________________________________________________________________________________________________
tf.stack_8 (TFOpLambda) (None, None, 2) 0 tf.meshgrid_2[0][0]
tf.meshgrid_2[0][1]
__________________________________________________________________________________________________
tf.__operators__.getitem (Slici () 0 tf.compat.v1.shape[0][0]
__________________________________________________________________________________________________
tf.expand_dims (TFOpLambda) (None, None, 1, 2) 0 tf.stack_2[0][0]
__________________________________________________________________________________________________
tf.__operators__.getitem_4 (Sli () 0 tf.compat.v1.shape_1[0][0]
__________________________________________________________________________________________________
tf.expand_dims_2 (TFOpLambda) (None, None, 1, 2) 0 tf.stack_5[0][0]
__________________________________________________________________________________________________
tf.__operators__.getitem_8 (Sli () 0 tf.compat.v1.shape_2[0][0]
__________________________________________________________________________________________________
tf.expand_dims_4 (TFOpLambda) (None, None, 1, 2) 0 tf.stack_8[0][0]
__________________________________________________________________________________________________
tf.reshape (TFOpLambda) (None, None, None, 3 0 conv2d_74[0][0]
tf.__operators__.getitem[0][0]
tf.__operators__.getitem_1[0][0]
tf.__operators__.getitem_1[0][0]
__________________________________________________________________________________________________
tf.expand_dims_1 (TFOpLambda) (1, None, None, 1, 2 0 tf.expand_dims[0][0]
__________________________________________________________________________________________________
tf.reshape_3 (TFOpLambda) (None, None, None, 3 0 conv2d_66[0][0]
tf.__operators__.getitem_4[0][0]
tf.__operators__.getitem_5[0][0]
tf.__operators__.getitem_5[0][0]
__________________________________________________________________________________________________
tf.expand_dims_3 (TFOpLambda) (1, None, None, 1, 2 0 tf.expand_dims_2[0][0]
__________________________________________________________________________________________________
tf.reshape_6 (TFOpLambda) (None, None, None, 3 0 conv2d_58[0][0]
tf.__operators__.getitem_8[0][0]
tf.__operators__.getitem_9[0][0]
tf.__operators__.getitem_9[0][0]
__________________________________________________________________________________________________
tf.expand_dims_5 (TFOpLambda) (1, None, None, 1, 2 0 tf.expand_dims_4[0][0]
__________________________________________________________________________________________________
tf.split (TFOpLambda) [(None, None, None, 0 tf.reshape[0][0]
__________________________________________________________________________________________________
tf.tile (TFOpLambda) (None, None, None, 3 0 tf.expand_dims_1[0][0]
tf.__operators__.getitem[0][0]
__________________________________________________________________________________________________
tf.split_1 (TFOpLambda) [(None, None, None, 0 tf.reshape_3[0][0]
__________________________________________________________________________________________________
tf.tile_1 (TFOpLambda) (None, None, None, 3 0 tf.expand_dims_3[0][0]
tf.__operators__.getitem_4[0][0]
__________________________________________________________________________________________________
tf.split_2 (TFOpLambda) [(None, None, None, 0 tf.reshape_6[0][0]
__________________________________________________________________________________________________
tf.tile_2 (TFOpLambda) (None, None, None, 3 0 tf.expand_dims_5[0][0]
tf.__operators__.getitem_8[0][0]
__________________________________________________________________________________________________
tf.math.sigmoid (TFOpLambda) (None, None, None, 3 0 tf.split[0][0]
__________________________________________________________________________________________________
tf.cast (TFOpLambda) (None, None, None, 3 0 tf.tile[0][0]
__________________________________________________________________________________________________
tf.math.exp (TFOpLambda) (None, None, None, 3 0 tf.split[0][1]
__________________________________________________________________________________________________
tf.math.sigmoid_3 (TFOpLambda) (None, None, None, 3 0 tf.split_1[0][0]
__________________________________________________________________________________________________
tf.cast_1 (TFOpLambda) (None, None, None, 3 0 tf.tile_1[0][0]
__________________________________________________________________________________________________
tf.math.exp_1 (TFOpLambda) (None, None, None, 3 0 tf.split_1[0][1]
__________________________________________________________________________________________________
tf.math.sigmoid_6 (TFOpLambda) (None, None, None, 3 0 tf.split_2[0][0]
__________________________________________________________________________________________________
tf.cast_2 (TFOpLambda) (None, None, None, 3 0 tf.tile_2[0][0]
__________________________________________________________________________________________________
tf.math.exp_2 (TFOpLambda) (None, None, None, 3 0 tf.split_2[0][1]
__________________________________________________________________________________________________
tf.__operators__.add_23 (TFOpLa (None, None, None, 3 0 tf.math.sigmoid[0][0]
tf.cast[0][0]
__________________________________________________________________________________________________
tf.math.multiply_1 (TFOpLambda) (None, None, None, 3 0 tf.math.exp[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_24 (TFOpLa (None, None, None, 3 0 tf.math.sigmoid_3[0][0]
tf.cast_1[0][0]
__________________________________________________________________________________________________
tf.math.multiply_4 (TFOpLambda) (None, None, None, 3 0 tf.math.exp_1[0][0]
__________________________________________________________________________________________________
tf.__operators__.add_25 (TFOpLa (None, None, None, 3 0 tf.math.sigmoid_6[0][0]
tf.cast_2[0][0]
__________________________________________________________________________________________________
tf.math.multiply_7 (TFOpLambda) (None, None, None, 3 0 tf.math.exp_2[0][0]
__________________________________________________________________________________________________
tf.math.multiply (TFOpLambda) (None, None, None, 3 0 tf.__operators__.add_23[0][0]
__________________________________________________________________________________________________
tf.math.multiply_2 (TFOpLambda) (None, None, None, 3 0 tf.math.multiply_1[0][0]
__________________________________________________________________________________________________
tf.math.multiply_3 (TFOpLambda) (None, None, None, 3 0 tf.__operators__.add_24[0][0]
__________________________________________________________________________________________________
tf.math.multiply_5 (TFOpLambda) (None, None, None, 3 0 tf.math.multiply_4[0][0]
__________________________________________________________________________________________________
tf.math.multiply_6 (TFOpLambda) (None, None, None, 3 0 tf.__operators__.add_25[0][0]
__________________________________________________________________________________________________
tf.math.multiply_8 (TFOpLambda) (None, None, None, 3 0 tf.math.multiply_7[0][0]
__________________________________________________________________________________________________
tf.concat_2 (TFOpLambda) (None, None, None, 3 0 tf.math.multiply[0][0]
tf.math.multiply_2[0][0]
__________________________________________________________________________________________________
tf.math.sigmoid_1 (TFOpLambda) (None, None, None, 3 0 tf.split[0][2]
__________________________________________________________________________________________________
tf.math.sigmoid_2 (TFOpLambda) (None, None, None, 3 0 tf.split[0][3]
__________________________________________________________________________________________________
tf.concat_4 (TFOpLambda) (None, None, None, 3 0 tf.math.multiply_3[0][0]
tf.math.multiply_5[0][0]
__________________________________________________________________________________________________
tf.math.sigmoid_4 (TFOpLambda) (None, None, None, 3 0 tf.split_1[0][2]
__________________________________________________________________________________________________
tf.math.sigmoid_5 (TFOpLambda) (None, None, None, 3 0 tf.split_1[0][3]
__________________________________________________________________________________________________
tf.concat_6 (TFOpLambda) (None, None, None, 3 0 tf.math.multiply_6[0][0]
tf.math.multiply_8[0][0]
__________________________________________________________________________________________________
tf.math.sigmoid_7 (TFOpLambda) (None, None, None, 3 0 tf.split_2[0][2]
__________________________________________________________________________________________________
tf.math.sigmoid_8 (TFOpLambda) (None, None, None, 3 0 tf.split_2[0][3]
__________________________________________________________________________________________________
tf.concat_3 (TFOpLambda) (None, None, None, 3 0 tf.concat_2[0][0]
tf.math.sigmoid_1[0][0]
tf.math.sigmoid_2[0][0]
__________________________________________________________________________________________________
tf.concat_5 (TFOpLambda) (None, None, None, 3 0 tf.concat_4[0][0]
tf.math.sigmoid_4[0][0]
tf.math.sigmoid_5[0][0]
__________________________________________________________________________________________________
tf.concat_7 (TFOpLambda) (None, None, None, 3 0 tf.concat_6[0][0]
tf.math.sigmoid_7[0][0]
tf.math.sigmoid_8[0][0]
==================================================================================================
Total params: 61,576,342
Trainable params: 61,523,734
Non-trainable params: 52,608
__________________________________________________________________________________________________
from trulens.
Related Issues (20)
- Rag evaluation with TruLens and bedrock not working using query engine retriever HOT 1
- ArrowInvalid: ('cannot mix struct and non-struct, non-null values', 'Conversion failed for column statement with type object')
- TruLlama with query engine argument not working HOT 4
- Exception in LangChain causes TruLens evaluation to halt HOT 2
- Custom Retriever Class for AWS Bedrock + Retriever Class HOT 9
- Unhandled Exception in feedback function HOT 2
- please change the import of PromptTemplate from langchain.prompts HOT 1
- Custom Feedback Provider HOT 1
- TypeError in trulens: issubclass() Argument Must Be a Class When Wrapping RAG with TruCustomApp HOT 4
- Issue with Trulens Evaluation and TruChain(using LangChain) HOT 1
- OpenAI account Terminated after using trulens library HOT 3
- Consistent format expectations for all Bedrock models HOT 10
- LiteLLM required when it shouldn't be
- Arbitrary LLM endpoint as Provider
- AttributeError: module 'openai' has no attribute 'OpenAI' HOT 1
- Error when using Ground Truth HOT 2
- Improve docs for litellm usage with local models
- Add docs for running evals on pre-logged data HOT 10
- AssertionError using LangChain's ChatOpenAI with `streaming=true` HOT 3
- error "name 'Bedrock' is not defined" when groundedness is calculated HOT 8
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from trulens.