How to convert shape=(1, 299, 299, 3) to expected shape=(None, 299, 299, 3) to feed into trained inception v3 model.
NOTE: THE SAME QUESTION HAVE BEEN ASKED BEFORE BUT THE ANSWER ISN'T CLEAR ENOUGH.
img = tf.io.read_file(img)
# decode image into tensor
img = tf.io.decode_image(img,channels=3) # hardcode for 3 channels to be compatible despite of the image type
# resize the image
img = tf.image.resize(img,[229,229])
# Scale Y/N
img = img/255.
img.shape
TensorShape([229, 229, 3])
instance = np.expand_dims(img, axis=0)
print(instance.shape)
(1, 229, 229, 3)
predictions = model(instance).numpy().argmax(axis=1)
An error occurred when trying to get a prediction as follows. ValueError: Input 0 is incompatible with layer inception_v3: expected shape=(None, 299, 299, 3), found shape=(None, 229, 229, 3) --------------------------------------------------------------------------- ValueError Traceback (most recent call last) in () ----> 1 predictions = model(instance).numpy().argmax(axis=1)
1 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
267 ' is incompatible with layer ' layer_name
268 ': expected shape=' str(spec.shape)
--> 269 ', found shape=' display_shape(x.shape))
270
271
ValueError: Input 0 is incompatible with layer inception_v3: expected shape=(None, 299, 299, 3), found shape=(1, 229, 229, 3)
According to answer 01 I changed the code as follows and encounter some peculiar errors.
img = tf.expand_dims(img,axis=0)
img = tf.keras.applications.inception_v3.preprocess_input(img)
predictions = model.predict(img).argmax(axis=1)
The new error is as follows
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-130-1d94d955d14c> in <module>()
----> 1 predictions = model.predict(img).argmax(axis=1)
9 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
1749 for step in data_handler.steps():
1750 callbacks.on_predict_batch_begin(step)
-> 1751 tmp_batch_outputs = self.predict_function(iterator)
1752 if data_handler.should_sync:
1753 context.async_wait()
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
883
884 with OptionalXlaContext(self._jit_compile):
--> 885 result = self._call(*args, **kwds)
886
887 new_tracing_count = self.experimental_get_tracing_count()
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
931 # This is the first call of __call__, so we have to initialize.
932 initializers = []
--> 933 self._initialize(args, kwds, add_initializers_to=initializers)
934 finally:
935 # At this point we know that the initialization is complete (or less
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
758 self._concrete_stateful_fn = (
759 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 760 *args, **kwds))
761
762 def invalid_creator_scope(*unused_args, **unused_kwds):
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
3064 args, kwargs = None, None
3065 with self._lock:
-> 3066 graph_function, _ = self._maybe_define_function(args, kwargs)
3067 return graph_function
3068
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
3461
3462 self._function_cache.missed.add(call_context_key)
-> 3463 graph_function = self._create_graph_function(args, kwargs)
3464 self._function_cache.primary[cache_key] = graph_function
3465
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3306 arg_names=arg_names,
3307 override_flat_arg_shapes=override_flat_arg_shapes,
-> 3308 capture_by_value=self._capture_by_value),
3309 self._function_attributes,
3310 function_spec=self.function_spec,
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
1005 _, original_func = tf_decorator.unwrap(python_func)
1006
-> 1007 func_outputs = python_func(*func_args, **func_kwargs)
1008
1009 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
666 # the function a weak reference to itself to avoid a reference cycle.
667 with OptionalXlaContext(compile_with_xla):
--> 668 out = weak_wrapped_fn().__wrapped__(*args, **kwds)
669 return out
670
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
992 except Exception as e: # pylint:disable=broad-except
993 if hasattr(e, "ag_error_metadata"):
--> 994 raise e.ag_error_metadata.to_exception(e)
995 else:
996 raise
ValueError: in user code:
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:1586 predict_function *
return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:1576 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1286 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2849 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3632 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:1569 run_step **
outputs = model.predict_step(data)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:1537 predict_step
return self(x, training=False)
/usr/local/lib/python3.7/dist-packages/keras/engine/base_layer.py:1020 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py:269 assert_input_compatibility
', found shape=' display_shape(x.shape))
ValueError: Input 0 is incompatible with layer inception_v3: expected shape=(None, 299, 299, 3), found shape=(None, 229, 229, 3)
CodePudding user response：
You should use tf.expand_dims to add a new dimension to your existing tensor. And calling inception_v3.preprocess_input will scale input pixels between -1 and 1 for you:
import tensorflow as tf
model = tf.keras.applications.InceptionV3()
image = tf.random.normal((299, 299, 3))
image = tf.expand_dims(image, axis=0)
image = tf.keras.applications.inception_v3.preprocess_input(image)
preds = model.predict(image)
print(preds.argmax(axis=1))
[111]
You are resizing your image with the wrong dimensions. Instead of [229,229] you need [299,299]. Try this:
import tensorflow as tf
import numpy as np
model = tf.keras.applications.inception_v3.InceptionV3(weights="imagenet")
x = tf.io.read_file('dog.jpeg')
x = tf.io.decode_image(x,channels=3)
x = tf.image.resize(x,[299,299])
x = tf.expand_dims(x, axis=0)
x = tf.keras.applications.inception_v3.preprocess_input(x)
preds = model.predict(x)
print(preds.argmax(axis=1))
[158]