Problem in visualizing attention with custom model

[viet2411]

Hello,
I'm getting trouble in using keras-vis for visualizing attention of the model.
Below is my model's architecture:

---

input_1 (InputLayer) (None, 224, 224, 3) 0

---

block1_conv1 (Conv2D) (None, 224, 224, 64) 1792

---

block1_conv2 (Conv2D) (None, 224, 224, 64) 36928

---

block1_pool (MaxPooling2D) (None, 112, 112, 64) 0

---

block2_conv1 (Conv2D) (None, 112, 112, 128) 73856

---

block2_conv2 (Conv2D) (None, 112, 112, 128) 147584

---

block2_pool (MaxPooling2D) (None, 56, 56, 128) 0

---

block3_conv1 (Conv2D) (None, 56, 56, 256) 295168

---

block3_conv2 (Conv2D) (None, 56, 56, 256) 590080

---

block3_conv3 (Conv2D) (None, 56, 56, 256) 590080

---

block3_pool (MaxPooling2D) (None, 28, 28, 256) 0

---

block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160

---

block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808

---

block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808

---

block4_pool (MaxPooling2D) (None, 14, 14, 512) 0

---

block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808

---

block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808

---

block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808

---

block5_pool (MaxPooling2D) (None, 7, 7, 512) 0

---

flatten (Flatten) (None, 25088) 0

---

fc1 (Dense) (None, 256) 6422784

---

dropout_1 (Dropout) (None, 256) 0

---

predictions (Dense) (None, 7) 1799

and I received this error :

`raceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1607, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: slice index 20 of dimension 1 out of bounds. for 'strided_slice' (op: 'StridedSlice') with input shapes: [?,7], [2], [2], [2] and with computed input tensors: input[1] = <0 20>, input[2] = <0 21>, input[3] = <1 1>.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:/Projects/Visualization/visual.py", line 37, in
seed_input=img, backprop_modifier=modifier)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\vis\visualization\saliency.py", line 134, in visualize_saliency
return visualize_saliency_with_losses(model.input, losses, seed_input, wrt_tensor, grad_modifier, keepdims)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\vis\visualization\saliency.py", line 78, in visualize_saliency_with_losses
opt = Optimizer(input_tensor, losses, wrt_tensor=wrt_tensor, norm_grads=False)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\vis\optimizer.py", line 52, in init
loss_fn = weight * loss.build_loss()
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\vis\losses.py", line 84, in build_loss
loss += -K.mean(layer_output[:, idx])
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\ops\array_ops.py", line 802, in _slice_helper
name=name)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\ops\array_ops.py", line 968, in strided_slice
shrink_axis_mask=shrink_axis_mask)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\ops\gen_array_ops.py", line 10392, in strided_slice
shrink_axis_mask=shrink_axis_mask, name=name)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\framework\op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1770, in init
control_input_ops)
File "C:\ProgramData\Anaconda3\envs\Projects\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1610, in _create_c_op
raise ValueError(str(e))
ValueError: slice index 20 of dimension 1 out of bounds. for 'strided_slice' (op: 'StridedSlice') with input shapes: [?,7], [2], [2], [2] and with computed input tensors: input[1] = <0 20>, input[2] = <0 21>, input[3] = <1 1>.
`

[sharpant]

I think your index 20 is out of bounds because you may not have 20 classes in your custom model.