Gradient clipping needs to happen after computing the gradients, but before applying them to update the model’s parameters. In your example, both of those things are handled by the AdamOptimizer.minimize() method. In order to clip your gradients you’ll need to explicitly compute, clip, and apply them as described in this section in TensorFlow’s API documentation. … Read more
If you want to force Keras to use CPU Way 1 import os os.environ[“CUDA_DEVICE_ORDER”] = “PCI_BUS_ID” # see issue #152 os.environ[“CUDA_VISIBLE_DEVICES”] = “” before Keras / Tensorflow is imported. Way 2 Run your script as $ CUDA_VISIBLE_DEVICES=”” ./your_keras_code.py See also https://github.com/keras-team/keras/issues/152 https://github.com/fchollet/keras/issues/4613
If you have this error after an upgrade to TensorFlow 2.0, you can still use 1.X API by replacing: import tensorflow as tf by import tensorflow.compat.v1 as tf tf.disable_v2_behavior()
The tf.app.flags module is presently a thin wrapper around python-gflags, so the documentation for that project is the best resource for how to use it argparse, which implements a subset of the functionality in python-gflags. Note that this module is currently packaged as a convenience for writing demo apps, and is not technically part of … Read more
Having two different functions is a convenience, as they produce the same result. The difference is simple: For sparse_softmax_cross_entropy_with_logits, labels must have the shape [batch_size] and the dtype int32 or int64. Each label is an int in range [0, num_classes-1]. For softmax_cross_entropy_with_logits, labels must have the shape [batch_size, num_classes] and dtype float32 or float64. Labels … Read more
It depends. ADAM updates any parameter with an individual learning rate. This means that every parameter in the network has a specific learning rate associated. But the single learning rate for each parameter is computed using lambda (the initial learning rate) as an upper limit. This means that every single learning rate can vary from … Read more
The pooling and convolutional ops slide a “window” across the input tensor. Using tf.nn.conv2d as an example: If the input tensor has 4 dimensions: [batch, height, width, channels], then the convolution operates on a 2D window on the height, width dimensions. strides determines how much the window shifts by in each of the dimensions. The … Read more
Keras has now added Train / validation split from a single directory using ImageDataGenerator: train_datagen = ImageDataGenerator(rescale=1./255, shear_range=0.2, zoom_range=0.2, horizontal_flip=True, validation_split=0.2) # set validation split train_generator = train_datagen.flow_from_directory( train_data_dir, target_size=(img_height, img_width), batch_size=batch_size, class_mode=”binary”, subset=”training”) # set as training data validation_generator = train_datagen.flow_from_directory( train_data_dir, # same directory as training data target_size=(img_height, img_width), batch_size=batch_size, class_mode=”binary”, subset=”validation”) # … Read more
TL;DR Despite their similar names, these arguments have quite difference meanings. The buffer_size in Dataset.shuffle() can affect the randomness of your dataset, and hence the order in which elements are produced. The buffer_size in Dataset.prefetch() only affects the time it takes to produce the next element. The buffer_size argument in tf.data.Dataset.prefetch() and the output_buffer_size argument … Read more
Try this: with tf.Session() as sess: saver = tf.train.import_meta_graph(‘/tmp/model.ckpt.meta’) saver.restore(sess, “/tmp/model.ckpt”) The TensorFlow save method saves three kinds of files because it stores the graph structure separately from the variable values. The .meta file describes the saved graph structure, so you need to import it before restoring the checkpoint (otherwise it doesn’t know what variables … Read more