Feeding image data in tensorflow for transfer learning

Question

I am trying to use tensorflow for transfer learning. I downloaded the pre-trained model inception3 from the tutorial. In the code, for prediction:

predictio         


        

Answer 1

The shipped InceptionV3 graph used in classify_image.py only supports JPEG images out-of-the-box. There are two ways you could use this graph with PNG images:

1. Convert the PNG image to a height x width x 3 (channels) Numpy array, for example using PIL, then feed the 'DecodeJpeg:0' tensor:

   import numpy as np
   from PIL import Image
   # ...
   
   image = Image.open("example.png")
   image_array = np.array(image)[:, :, 0:3]  # Select RGB channels only.
   
   prediction = sess.run(softmax_tensor, {'DecodeJpeg:0': image_array})
   

   Perhaps confusingly, 'DecodeJpeg:0' is the output of the DecodeJpeg op, so by feeding this tensor, you are able to feed raw image data.

2. Add a tf.image.decode_png() op to the imported graph. Simply switching the name of the fed tensor from 'DecodeJpeg/contents:0' to 'DecodePng/contents:0' does not work because there is no 'DecodePng' op in the shipped graph. You can add such a node to the graph by using the input_map argument to tf.import_graph_def():

   png_data = tf.placeholder(tf.string, shape=[])
   decoded_png = tf.image.decode_png(png_data, channels=3)
   # ...
   
   graph_def = ...
   softmax_tensor = tf.import_graph_def(
       graph_def,
       input_map={'DecodeJpeg:0': decoded_png},
       return_elements=['softmax:0'])
   
   sess.run(softmax_tensor, {png_data: ...})