CODEWITHSUNDEEP
pythontensorflowmachine-learninginferencepre-trained-model
C.H.Song
C.H.Song

Reputation: 41

Pretrained Tensorflow Model invalid argument error

I'm doing my project using tensorflow with pre-trained mobilenet_v2 model which can be found on https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md

I wanted to get hidden layer values so I implemented this source code and I got an invalidargumenterror

if __name__ == '__main__':
    im = Image.open('./sample/maltiz.png')
    im3 = im.resize((300, 300))

    image = np.asarray(im)[:,:,:3]

    model_path = 'models/ssd_mobilenet_v2_coco_2018_03_29/'

    meta_path = os.path.join(model_path, 'model.ckpt.meta')
    model = tf.train.import_meta_graph(meta_path)

    sess = tf.Session()
    model.restore(sess, tf.train.latest_checkpoint(model_path))

    data = np.array([image])
    data = data.astype(np.uint8)

    X = tf.placeholder(tf.uint8, shape=[None, None, None, 3])

    graph = tf.get_default_graph()

    for i in graph.get_operations():
        if "Relu" in i.name:
            print(sess.run(i.values(), feed_dict = { X : data}))

I got this error message

File "load_model.py", line 42, in <module>

    print(sess.run(i.values(), feed_dict = { X : data}))
InvalidArgumentError: You must feed a value for placeholder tensor 'image_tensor' with dtype uint8 and shape [?,?,?,3]

[[node image_tensor (defined at load_model.py:24) ]]

I printed out the placeholder and the shape of data.

placeholder was uint8 typed [?,?,?,3] and image had a shape with [1,300,300,3] I don't know what is the problem.

It looks like just perfect matching with the type on the error message.

Please let me know what is the problem.

Upvotes: 0

Views: 786

Answers (1)

Danny Fang
Danny Fang

Reputation: 4071

When you load the predefined graph and restore the graph to the latest checkpoint, the graph is already defined. But when you do

X = tf.placeholder(tf.uint8, shape=[None, None, None, 3])

You are creating an extra node in the graph. and this node has nothing to do with the nodes you want to evaluate, nodes from graph.get_operations() don't depend on this extra node but some other node, and since this other node does not get fed with values, the error says invalid arguments.

The correct way is to get the tensor that the nodes to be evaluated depend upon from the predefined graph.

im = Image.open('./sample/maltiz.png')
im3 = im.resize((300, 300))

image = np.asarray(im)[:,:,:3]

model_path = 'models/ssd_mobilenet_v2_coco_2018_03_29/'

meta_path = os.path.join(model_path, 'model.ckpt.meta')
model = tf.train.import_meta_graph(meta_path)

sess = tf.Session()
model.restore(sess, tf.train.latest_checkpoint(model_path))

data = np.array([image])
data = data.astype(np.uint8)

graph = tf.get_default_graph()
X = graph.get_tensor_by_name('image_tensor:0')

for i in graph.get_operations():
    if "Relu" in i.name:
        print(sess.run(i.values(), feed_dict = { X : data}))

PS: I did try the above approach myself but there is some tensorflow (version 1.13.1) internal bug which stops me from evaluating all the nodes that have Relu in their names. But still some nodes can be evaluated this way.

Upvotes: 1

Related Questions