Trying the first example about ai-blocks HOT 5 CLOSED

treid running a second time and got this:
Traceback (most recent call last):
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 686, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 784 and 1024 for 'MatMul' (op: 'MatMul') with input shapes: [?,784], [1024,256].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\lorenzo\AppData\Local\Temp/main.py", line 1524, in
instance_0.Run()
File "C:\Users\lorenzo\AppData\Local\Temp/main.py", line 861, in Run
_y = self._model.Run(self.X)
File "C:\Users\lorenzo\AppData\Local\Temp/main.py", line 1046, in Run
graph = self.model_elements[e].Run(graph, reuse=reuse)
File "C:\Users\lorenzo\AppData\Local\Temp/main.py", line 1181, in Run
h = tf.matmul(h, W) + b
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\math_ops.py", line 1891, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 2436, in _mat_mul
name=name)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 2958, in create_op
set_shapes_for_outputs(ret)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 2209, in set_shapes_for_outputs
shapes = shape_func(op)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 2159, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 627, in call_cpp_shape_fn
require_shape_fn)
File "C:\Users\lorenzo\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 691, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 784 and 1024 for 'MatMul' (op: 'MatMul') with input shapes: [?,784], [1024,256].

from ai-blocks.

Hi, that example is quite old, just select the neuron object in the scene and replace 1024 with 784 in the "hidden" array from the properties panel. I will replace the example project, sorry about that.

from ai-blocks.

yeah working now

from ai-blocks.

is that correct? https://ibb.co/d3X7HG

from ai-blocks.

Yes this is the expected behavior, I am closing the ticket.

from ai-blocks.