ValueError: Can't convert Python sequence with mixed types to Tensor.

[vigkrish123]

While running the code, I get this ValueError in yolo.py in line 28 :-
cell_x = tf.compat.v1.to_float(tf.reshape(tf.tile(tf.range(max_grid_w), [max_grid_h]), (1, max_grid_h, max_grid_w, 1, 1)))
cell_y = tf.transpose(cell_x, (0,2,1,3,4))
self.cell_grid = tf.tile(tf.concat([cell_x,cell_y],-1), [batch_size, 1, 1, 3, 1])

The full error message:-
Traceback (most recent call last):
File "train.py", line 293, in
main(args)
File "train.py", line 238, in main
train_model, infer_model = create_model(
File "train.py", line 145, in create_model
template_model, infer_model = create_yolov3_model(
File "C:\Users\vigne\yolo.py", line 300, in create_yolov3_model
loss_yolo_1 = YoloLayer(anchors[12:],
File "C:\Users\vigne\yolo.py", line 28, in init
self.cell_grid = tf.tile(tf.concat([cell_x,cell_y],-1), [batch_size, 1, 1, 3, 1])
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 11453, in tile
return tile_eager_fallback(
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 11490, in tile_eager_fallback
_attr_Tmultiples, (multiples,) = _execute.args_to_matching_eager([multiples], ctx, [_dtypes.int32, _dtypes.int64, ], _dtypes.int32)
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\eager\execute.py", line 265, in args_to_matching_eager
tensor = ops.convert_to_tensor(t, ctx=ctx)
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\profiler\trace.py", line 163, in wrapped
return func(*args, **kwargs)
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1540, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\framework\constant_op.py", line 339, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\framework\constant_op.py", line 264, in constant
return _constant_impl(value, dtype, shape, name, verify_shape=False,
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\framework\constant_op.py", line 276, in _constant_impl
return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\framework\constant_op.py", line 301, in _constant_eager_impl
t = convert_to_eager_tensor(value, ctx, dtype)
File "C:\Users\vigne\anaconda3\lib\site-packages\tensorflow\python\framework\constant_op.py", line 98, in convert_to_eager_tensor
return ops.EagerTensor(value, ctx.device_name, dtype)
ValueError: Can't convert Python sequence with mixed types to Tensor.

Any suggestion or solution would be helpful. Thanks

[MARGERY-R]

同问！！！！！！！！！

[helloxjade]

同问