I'm trying to optimize the input pipeline for .h5 data with tf.data. But I encountered a TypeError: expected str, bytes or os.PathLike object, not Tensor. I did a research but can't find anything about converting a tensor of string to string.
This simplified code is executable and return the same error:
batch_size = 1000 conv_size = 3 nb_conv = 32 learning_rate = 0.0001 # define parser function def parse_function(fname): with h5py.File(fname, 'r') as f: #Error comes from here X = f['X'].reshape(batch_size, patch_size, patch_size, 1) y = f['y'].reshape(batch_size, patch_size, patch_size, 1) return X, y # create a list of files path flist = [] for dirpath, _, fnames in os.walk('./proc/'): for fname in fnames: if fname.startswith('{}_{}'.format(patch_size, batch_size)) and fname.endswith('h5'): flist.append(fname) # prefetch data dataset = tf.data.Dataset.from_tensor_slices((flist)) dataset = dataset.shuffle(len(flist)) dataset = dataset.map(parse_function, num_parallel_calls=4) dataset = dataset.batch(1) dataset = dataset.prefetch(3) # simplest model that I think of X_ph = tf.placeholder(tf.float32, shape=None) y_ph = tf.placeholder(tf.float32, shape=None) W = tf.get_variable('w', shape=[conv_size, conv_size, 1, 1], initializer=tf.contrib.layers.xavier_initializer()) loss = tf.reduce_mean(tf.losses.mean_squared_error(tf.nn.softmax(labels=y_ph, predictions=tf.matmul(X_ph, W)))) train_op = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss) # start session with tf.Session() as sess: sess.run(tf.global_variables_initializer()) print(sess.run(train_op, feed_dict={X_ph: dataset[0], y_ph: dataset[1]})) Apparently the fname is a tensor of string but the positional argument waits for only a string. I can't find any documentation on this. And the answer of another post doesn't solve this problem. In my case, I work only with h5 where one h5 store one batch.
Update Solution: Thanks to the comment of @kvish, the part of loading .h5 file is solved. The code is upgraded with a simple conv layer, the placeholders have been taken. Each .h5 is one batch. I want to prefetch in parallele multiple batches(h5py doesn't support multithread reading so I write batches into multiple files). One can copy-paste-and-launch:
import h5py import threading import numpy as np import tensorflow as tf # generate some img data for i in range(5): with h5py.File('./test_{}.h5'.format(i), 'w') as f: f.create_dataset('X', shape=(1000, 100, 100), dtype='float32', data=np.random.rand(10**7).reshape(1000, 100, 100)) f.create_dataset('y', shape=(1000, 100, 100), dtype='float32', data=np.random.rand(10**7).reshape(1000, 100, 100)) print(threading.get_ident()) # params num_cores = 3 shuffle_size = 1 batch_size = 1 # read .h5 file def parse_file(f): print(f.decode('utf-8')) with h5py.File(f.decode("utf-8"), 'r') as fi: X = fi['X'][:].reshape(1000, 100, 100, 1) y = fi['y'][:].reshape(1000, 100, 100, 1) print(threading.get_ident()) # to see the thread id return X, y # py_func wrapper def parse_file_tf(filename): return tf.py_func(parse_file, [filename], [tf.float32, tf.float32]) # tf.data input pipeline files = tf.data.Dataset.list_files('./test_*.h5') dataset = files.map(parse_file_tf, num_parallel_calls=num_core) dataset = dataset.batch(batch_size).shuffle(shuffle_size).prefetch(3) it = dataset.make_initializable_iterator() iter_init_op = it.initializer X_it, y_it = it.get_next() # simplest model that I can think of with tf.name_scope("Conv1"): W = tf.get_variable("W", shape=[3, 3, 1, 1], initializer=tf.contrib.layers.xavier_initializer()) b = tf.get_variable("b", shape=[1], initializer=tf.contrib.layers.xavier_initializer()) layer1 = tf.nn.conv2d(X_it, W, strides=[1, 1, 1, 1], padding='SAME') + b out = tf.nn.relu(layer1) loss = tf.reduce_mean(tf.losses.mean_squared_error(labels=y_it, predictions=out)) train_op = tf.train.AdamOptimizer(learning_rate=0.0001).minimize(loss) # session sess = tf.Session() sess.run(tf.global_variables_initializer()) sess.run(iter_init_op) sess.run([train_op]) sess.close() Somehow there will be another cudnn issue which isn't related to this post.
tensorflow-cpu v1.12: work fine
tensorflow-gpu v1.12: runtime issue happens
Traceback (most recent call last): File "/envs/tf/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call return fn(*args) File "/envs/tf/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/envs/tf/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.NotFoundError: No algorithm worked! [[{{node Conv1/Conv2D}} = Conv2D[T=DT_FLOAT, data_format="NCHW", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](gradients/Conv1/Conv2D_grad/Conv2DBackpropFilter-0-TransposeNHWCToNCHW-LayoutOptimizer, W/read)]] [[{{node mean_squared_error/num_present/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_2/_37}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_63_me...t/Switch_2", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]] tensorflow-cpu v1.12: works fine!
