Merge pull request #1185 from cshallue/master

Small clarification to documentation

im2txt/README.md

@@ -296,8 +296,12 @@ Your trained *Show and Tell* model can generate captions for any JPEG image! The
 following command line will generate captions for an image from the test set.
 
 ```shell
-# Directory containing model checkpoints.
-CHECKPOINT_DIR="${HOME}/im2txt/model/train"
+# Path to checkpoint file or a directory containing checkpoint files. Passing
+# a directory will only work if there is also a file named 'checkpoint' which
+# lists the available checkpoints in the directory. It will not work if you
+# point to a directory with just a copy of a model checkpoint: in that case,
+# you will need to pass the checkpoint path explicitly.
+CHECKPOINT_PATH="${HOME}/im2txt/model/train"
 
 # Vocabulary file generated by the preprocessing script.
 VOCAB_FILE="${HOME}/im2txt/data/mscoco/word_counts.txt"
@@ -314,7 +318,7 @@ export CUDA_VISIBLE_DEVICES=""
 
 # Run inference to generate captions.
 bazel-bin/im2txt/run_inference \
-  --checkpoint_path=${CHECKPOINT_DIR} \
+  --checkpoint_path=${CHECKPOINT_PATH} \
   --vocab_file=${VOCAB_FILE} \
   --input_files=${IMAGE_FILE}
 ```

im2txt/im2txt/run_inference.py

@@ -39,6 +39,8 @@ tf.flags.DEFINE_string("input_files", "",
                        "File pattern or comma-separated list of file patterns "
                        "of image files.")
 
+tf.logging.set_verbosity(tf.logging.INFO)
+
 
 def main(_):
   # Build the inference graph.