| def sample_gumbel(shape, eps=1e-20): | |
| """Sample from Gumbel(0, 1)""" | |
| U = tf.random_uniform(shape,minval=0,maxval=1) | |
| return -tf.log(-tf.log(U + eps) + eps) | |
| def gumbel_softmax_sample(logits, temperature): | |
| """ Draw a sample from the Gumbel-Softmax distribution""" | |
| y = logits + sample_gumbel(tf.shape(logits)) | |
| return tf.nn.softmax( y / temperature) |
| """ | |
| To generate dataset, make folder with each video's frames extracted into subdir. the dino codebase has code to do this easily. | |
| videos = glob.glob(os.path.join(SOURCE_DIR,"*.mp4"))[:num_videos_to_extract] | |
| for i, video in enumerate(videos): | |
| print(i) | |
| directory=os.path.join(OUTPUT_DIR, str(i)) | |
| if not os.path.exists(directory): | |
| os.makedirs(directory) | |
| _extract_frames_from_video(inp=video, out=directory) |
| # | |
| # Qt qmake integration with Google Protocol Buffers compiler protoc | |
| # | |
| # To compile protocol buffers with qt qmake, specify PROTOS variable and | |
| # include this file | |
| # | |
| # Example: | |
| # LIBS += /usr/lib/libprotobuf.so | |
| # PROTOS = a.proto b.proto | |
| # include(protobuf.pri) |
Here are instructions to set up TensorFlow dev environment on Docker if you are running Windows, and configure it so that you can access Jupyter Notebook from within the VM + edit files in your text editor of choice on your Windows machine.
First, install https://www.docker.com/docker-toolbox
Since this is Windows, creating the Docker group "docker" is not necessary.
| """ | |
| A lightweight experiment logbook for Jupyter/Colab-style ad hoc experiments. | |
| Let's say you generate a plot with Matplotlib and want to re-run your notebook with a | |
| different set of configurations and then compare the resulting plot to the one you saved (to see | |
| if the new configuration is better). | |
| # Saving experiments | |
| f = plt.gcf() | |
| elog.savefig(f, |
| #!/bin/env python | |
| # uses tf-slim from release 0.10.0 | |
| import tensorflow as tf | |
| slim = tf.contrib.slim | |
| batch = 13 | |
| in_height, in_width, in_channels = 7, 7, 512 |
| def _reduce_logmeanexp(x, axis, epsilon): | |
| """Numerically-stable (?) implementation of log-mean-exp. | |
| Args: | |
| x: The tensor to reduce. Should have numeric type. | |
| axis: The dimensions to reduce. If `None` (the default), | |
| reduces all dimensions. Must be in the range | |
| `[-rank(input_tensor), rank(input_tensor)]`. | |
| epsilon: Floating point scalar to avoid log-underflow. |
| for i in range(num_bijectors): | |
| bijectors.append(tfb.MaskedAutoregressiveFlow( | |
| shift_and_log_scale_fn=tfb.masked_autoregressive_default_template( | |
| hidden_layers=[512, 512]))) | |
| bijectors.append(tfb.Permute(permutation=[1, 0])) | |
| flow_bijector = tfb.Chain(list(reversed(bijectors[:-1]))) |
| class BatchNorm(tfb.Bijector): | |
| def __init__(self, eps=1e-5, decay=0.95, validate_args=False, name="batch_norm"): | |
| super(BatchNorm, self).__init__( | |
| event_ndims=1, validate_args=validate_args, name=name) | |
| self._vars_created = False | |
| self.eps = eps | |
| self.decay = decay | |
| def _create_vars(self, x): | |
| n = x.get_shape().as_list()[1] |
| loss = -tf.reduce_mean(dist.log_prob(x_samples)) | |
| train_op = tf.train.AdamOptimizer(1e-3).minimize(loss) | |
| sess = tf.InteractiveSession() | |
| sess.run(tf.global_variables_initializer()) | |
| NUM_STEPS = int(1e5) | |
| global_step = [] | |
| np_losses = [] | |
| for i in range(NUM_STEPS): | |
| _, np_loss = sess.run([train_op, loss]) | |
| if i % 1000 == 0: |