I have tried both the tensorflow models for tranfer learning. The models are
- inception_v3_2016_08_28.tar.gz - from tensorflow-models
- classify_image_graph_def.pb - comes along with tensorflow image_retraining code.
But the results i am getting are totally different. Where the second models performs way better than the first. Is it expected ? First model gives accuracy of 57% where the second model gives 80% accuracy.
The first model is checkpoint file. For transfer learning, i have converted the checkpoint file to protobuf file. Then the python code retrain.py which comes along with tensorflow is used to do the retraining. Following code is used to convert checkpoint file to a protobuf file.
checkpoint_file = '../check_points/inception_v3.ckpt'
decode_jpeg_data = tf.placeholder(tf.string)
decode_jpeg = tf.image.decode_jpeg(decode_jpeg_data, channels=3, dct_method="INTEGER_ACCURATE")
if decode_jpeg.dtype != tf.float32:
decode_jpeg = tf.image.convert_image_dtype(decode_jpeg, dtype=tf.float32)
image_ = tf.expand_dims(decode_jpeg, 0)
image = tf.image.resize_bicubic(image_, [299, 299], align_corners=True)
scaled_input_tensor = tf.scalar_mul((1.0/255), image)
scaled_input_tensor = tf.subtract(scaled_input_tensor, 0.5)
scaled_input_tensor = tf.multiply(scaled_input_tensor, 2.0)
# loading the inception graph
arg_scope = inception_v3_arg_scope()
with slim.arg_scope(arg_scope):
logits, end_points = inception_v3(inputs=scaled_input_tensor, is_training=False, num_classes=1001)
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess, checkpoint_file)
with gfile.FastGFile('./models/inceptionv3.pb', 'wb') as f:
f.write(output_graph_def.SerializeToString())
