convolutional-pose-machines-tensorflow
convolutional-pose-machines-tensorflow copied to clipboard
timctho
I am trying to train my hand pose model with your contribution， thanks. When I reading your code, I am a little confused about bg_img_dir(in config.py). Can u tell me...
Sorry, I want to know how to get Ensemble_data_generator? And can you tell which software can I use to make the train set fast ? Thank you!
g = Ensemble_data_generator.ensemble_data_generator(FLAGS.train_img_dir, FLAGS.bg_img_dir, FLAGS.batch_size, FLAGS.input_size, True, True, FLAGS.augmentation_config, FLAGS.hnm, FLAGS.do_cropping) g_eval = Ensemble_data_generator.ensemble_data_generator(FLAGS.val_img_dir, FLAGS.bg_img_dir, FLAGS.batch_size, FLAGS.input_size, True, True, FLAGS.augmentation_config, FLAGS.hnm, FLAGS.do_cropping) Hello, thanks for sharing. I have three questions:...
hello author, i see you have used only 3x3 and 7x7 filter size, any particular reason?
Hello, I found a performance issue in the definition of `read_and_decode_cpm`, utils/tf_utils.py, [tf.parse_single_example](https://github.com/timctho/convolutional-pose-machines-tensorflow/blob/b9a30fbb5a2f1d15faf8f553201203a431cb34cb/utils/tf_utils.py#L15) will created repeatedly during program execution, resulting in reduced efficiency. I think it should be created before...
When running the `run_freeze_graph.py` I get this error: ``` $ python3 run_freeze_graph.py /home/christian/anaconda3/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it...
I successfully converted the provide checkpoints (cpm_hand) to tflite model and presently trying to compile the tflite model for edge TPU. During compilation the edge TPU compiler provides the following...
