Related
How do I change the number of input channels in the torchvision ConvNeXt model? I am working with grayscale images and want 1 input channel instead of 3.
import torch
from torchvision.models.convnext import ConvNeXt, CNBlockConfig
# this is the given configuration for the 'tiny' model
block_setting = [
CNBlockConfig(96, 192, 3),
CNBlockConfig(192, 384, 3),
CNBlockConfig(384, 768, 9),
CNBlockConfig(768, None, 3),
]
model = ConvNeXt(block_setting)
# my sample image (N, C, W, H) = (16, 1, 50, 50)
im = torch.randn(16, 1, 50, 50)
# forward pass
model(im)
output:
RuntimeError: Given groups=1, weight of size [96, 3, 4, 4], expected input[16, 1, 50, 50] to have 3 channels, but got 1 channels instead
However, if I change my input shape to (16, 3, 50, 50) it seems to work fine.
The torchvision source code seems to be based of their github implementation but where do I specify in_chans with the torchvision interface?
You can rewrite the whole input layer, model._modules["features"][0][0] is
nn.Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4))
Then, you only need to change the in_channels
>>> model._modules["features"][0][0] = nn.Conv2d(1, 96, kernel_size=(4, 4), stride=(4, 4))
>>> model(im)
tensor([[-0.4854, -0.1925, 0.1051, ..., -0.2310, -0.8830, -0.0251],
[ 0.3332, -0.4205, -0.3007, ..., 0.8530, 0.1429, -0.3819],
[ 0.1794, -0.7546, -0.7835, ..., -0.8072, -0.0972, 0.7413],
...,
[ 0.1356, 0.0868, 0.6135, ..., -0.1382, -0.2001, 0.2415],
[-0.1612, -0.4812, 0.1271, ..., -0.6594, 0.2706, 1.0833],
[ 0.0243, -0.5039, -0.4086, ..., 0.4233, 0.0389, 0.2787]],
grad_fn=<AddmmBackward0>)
Using pretraining GloveVector from stanford to get the meaningful representation of each word but i want representations for a sentence containing 5-15 words, so that i can make use of cosine similarity to do a match when i receive a new sentence. I am setting a 15 words (fixed size) of each sentence and applied embedding layer then the new input shape is going to be 15 X 300 dimensions (If i have less than 15 words then padded values to make it 15 words (one random uniform distribution of 300D vector)
Below are my network shapes
[None, 15] -- Raw inputs embedding and padded(1) ID's
[None, 15, 300, 1], --input
[None, 8, 150, 128], -- conv 1
[None, 4, 75, 64], -- conv 2
[None, 2, 38, 32], -- conv 3
[None, 1, 19, 16], -- conv 4
[None, 1, 10, 4] -- conv 5
[None, 50] ---------Latent shape (new meaningful representati)------
[None, 1, 10, 4] -- encoded input for de-conv
[None, 1, 19, 16], -- conv_trans 5
[None, 2, 38, 32], -- conv_trans 4
[None, 4, 75, 64], -- conv_trans 3
[None, 8, 150, 128], -- conv_trans 2
[None, 15, 300, 1] -- conv_trans 1 -- for loss funtion with input
I have tried the CNN model with embedding layer in tensorflow
self._inputs = tf.placeholder(dtype=tf.int64, shape=[None, self.sent_len], name='input_x') #(?,15)
losses = []
# lookup layer
with tf.variable_scope('embedding') as scope:
self._W_emb = _variable_on_cpu(name='embedding', shape=[self.vocab_size, self.emb_size], initializer=tf.random_uniform_initializer(minval=-1.0, maxval=1.0))
# assigned pretrained embedding here, so initializer would be overrided
sent_batch = tf.nn.embedding_lookup(params=self._W_emb, ids=self._inputs)
sent_batch = tf.expand_dims(sent_batch, -1)
self._x = sent_batch
encoder = []
shapes = []
current_input = sent_batch
shapes.append(current_input.get_shape().as_list())
for layer_i, n_output in enumerate(n_filters[1:]):
with tf.variable_scope('Encode_conv-%d' % layer_i) as scope:
n_input = current_input.get_shape().as_list()[3]
W, wd = _variable_with_weight_decay('W-%d' % layer_i, shape=[filter_size,filter_size,n_input,n_output],
initializer=tf.random_uniform_initializer(minval=-1.0, maxval=1.0), wd=self.l2_reg)
losses.append(wd)
biases = _variable_on_cpu('bias-%d' % layer_i, shape=[n_output], initializer=tf.constant_initializer(0.00))
encoder.append(W)
output = tf.nn.relu(tf.add(tf.nn.conv2d(current_input, W, strides=[1, 2, 2, 1], padding='SAME'), biases), name=scope.name)
current_input = output
shapes.append(output.get_shape().as_list())
#z = current_input
original_shape = current_input.get_shape().as_list()
flatsize = original_shape[1]*original_shape[2]*original_shape[3]
height,width,channel = original_shape[1]*1,original_shape[2]*1,original_shape[3]*1
current_input = tf.reshape(current_input,[-1,flatsize])
with tf.variable_scope('Encode_Z-%d' % layer_i) as scope:
W_en, wd_en = _variable_with_weight_decay('W', shape=[current_input.get_shape().as_list()[1], outsize],
initializer=tf.truncated_normal_initializer(stddev=0.05),
wd=self.l2_reg)
losses.append(wd_en)
biases_en = _variable_on_cpu('bias', shape=[outsize],initializer=tf.constant_initializer(0.00))
self._z = tf.nn.relu(tf.nn.bias_add(tf.matmul(current_input, W_en), biases_en)) # Compressed representation (?,50)
with tf.variable_scope('Decode_Z-%d' % layer_i) as scope:
W_dc, wd_dc = _variable_with_weight_decay('W', shape=[self._z.get_shape().as_list()[1], current_input.get_shape().as_list()[1]],
initializer=tf.truncated_normal_initializer(stddev=0.05), wd=self.l2_reg)
losses.append(wd_dc)
biases_dc = _variable_on_cpu('bias', shape=[current_input.get_shape().as_list()[1]],initializer=tf.constant_initializer(0.00))
current_input = tf.nn.relu(tf.nn.bias_add(tf.matmul(self._z, W_dc), biases_dc))
current_input = tf.reshape(current_input,[-1,height,width,channel])
encoder.reverse()
shapes.reverse()
for layer_i, shape in enumerate(shapes[1:]):
with tf.variable_scope('Decode_conv-%d' % layer_i) as scope:
W = encoder[layer_i]
b = _variable_on_cpu('bias-%d' % layer_i, shape=[W.get_shape().as_list()[2]], initializer=tf.constant_initializer(0.00))
hh,ww,cc = shape[1], shape[2], shape[3]
output = tf.nn.relu(tf.add( tf.nn.conv2d_transpose(current_input, W, [tf.shape(sent_batch)[0],hh,ww,cc],strides=[1, 2, 2, 1],padding='SAME'), b),name=scope.name)
current_input = output
self._y = current_input
# loss
with tf.variable_scope('loss') as scope:
cross_entropy_loss = tf.reduce_mean(tf.square(current_input - sent_batch))
losses.append(cross_entropy_loss)
self._total_loss = tf.add_n(losses, name='total_loss')
opt = tf.train.AdamOptimizer(0.0001)
grads = opt.compute_gradients(self._total_loss)
self._train_op = opt.apply_gradients(grads)
But the results are not performing well because below two sentence cosine similarity is 0.9895 after getting the latent compressed representation from above model.
Functional disorders of polymorphonuclear neutrophils'
Unspecified fracture of skull, sequela'
And if i take sentences with 2-5 words and the similarity is going up to 0.9999 (suspecting the issue was caused by more default padding values with same uniform distribution from embedding lookups)
Below information may be helpful,
Total of 10,000 training samples with 10 epochs
Used Relu activations
MSE loss function
Adam optimizers
Below is the words distributions of over all sentence [
And finally can anyone suggest what's going wrong? and approach itself is not good to proceed?
I am trying to make a classifier based on capsule network, and I am able to train this network but have a problem with making a prediction. How my code should look like to make a prediction given an arbitrary image (I need an example). One important thing is that I'm using EM routing. In dynamic routing its enough to calculate length of vector of last capsule layer to get predicted class but how it is in EM routing?
Here is my code:
poses, activations = m_capsules.nets.capsules_net(images, num_classes=10, iterations=3,
batch_size=batch_size, name='capsules_em')
global_step = tf.train.get_or_create_global_step()
loss = m_capsules.nets.spread_loss(
labels, activations, iterations_per_epoch, global_step, name='spread_loss'
)
tf.summary.scalar('losses/spread_loss', loss)
optimizer = tf.train.AdamOptimizer(learning_rate=0.0005)
train_tensor = slim.learning.create_train_op(
loss, optimizer, global_step=global_step, clip_gradient_norm=4.0
)
slim.learning.train(
train_tensor,
logdir="./log/train",
log_every_n_steps=1,
save_summaries_secs=60,
saver=tf.train.Saver(max_to_keep=2),
save_interval_secs=600,
)
So far I was trying to write estimator but having trouble. Below is a code:
mnist_classifier = tf.estimator.Estimator(model_fn=m_capsules.nets.capsules_net, model_dir=dir)
prediction = mnist_classifier.predict(input_fn=words_input_fn)
And my model looks like:
def capsules_net(inputs, num_classes, iterations, batch_size, name='ocr-caps'):
"""Define the Capsule Network model
"""
with tf.variable_scope(name) as scope:
# ReLU Conv1
# Images shape (24, 28, 28, 1) -> conv 5x5 filters, 32 output channels, strides 2 with padding, ReLU
# nets -> (?, 14, 14, 32)
nets = conv2d(
inputs,
kernel=5, out_channels=26, stride=2, padding='SAME',
activation_fn=tf.nn.relu, name='relu_conv1'
)
# PrimaryCaps
# (?, 14, 14, 32) -> capsule 1x1 filter, 32 output capsule, strides 1 without padding
# nets -> (poses (?, 14, 14, 32, 4, 4), activations (?, 14, 14, 32))
nets = primary_caps(
nets,
kernel_size=1, out_capsules=26, stride=1, padding='VALID',
pose_shape=[4, 4], name='primary_caps'
)
# ConvCaps1
# (poses, activations) -> conv capsule, 3x3 kernels, strides 2, no padding
# nets -> (poses (24, 6, 6, 32, 4, 4), activations (24, 6, 6, 32))
nets = conv_capsule(
nets, shape=[3, 3, 26, 26], strides=[1, 2, 2, 1], iterations=iterations,
batch_size=batch_size, name='conv_caps1'
)
# ConvCaps2
# (poses, activations) -> conv capsule, 3x3 kernels, strides 1, no padding
# nets -> (poses (24, 4, 4, 32, 4, 4), activations (24, 4, 4, 32))
nets = conv_capsule(
nets, shape=[3, 3, 26, 26], strides=[1, 1, 1, 1], iterations=iterations,
batch_size=batch_size, name='conv_caps2'
)
# Class capsules
# (poses, activations) -> 1x1 convolution, 10 output capsules
# nets -> (poses (24, 10, 4, 4), activations (24, 10))
nets = class_capsules(nets, num_classes, iterations=iterations,
batch_size=batch_size, name='class_capsules')
# poses (24, 10, 4, 4), activations (24, 10)
poses, activations = nets
return poses, activations
I am attempting to stride over the channel dimension, and the following code exhibits surprising behaviour. It is my expectation that tf.nn.max_pool and tf.nn.avg_pool should produce tensors of identical shape when fed the exact same arguments. This is not the case.
import tensorflow as tf
x = tf.get_variable('x', shape=(100, 32, 32, 64),
initializer=tf.constant_initializer(5), dtype=tf.float32)
ksize = (1, 2, 2, 2)
strides = (1, 2, 2, 2)
max_pool = tf.nn.max_pool(x, ksize, strides, padding='SAME')
avg_pool = tf.nn.avg_pool(x, ksize, strides, padding='SAME')
print(max_pool.shape)
print(avg_pool.shape)
This prints
$ python ex04/mini.py
(100, 16, 16, 32)
(100, 16, 16, 64)
Clearly, I am misunderstanding something.
The link https://github.com/Hvass-Labs/TensorFlow-Tutorials/issues/19 states:
The first and last stride must always be 1,
because the first is for the image-number and
the last is for the input-channel.
Turns out this is really a bug.
https://github.com/tensorflow/tensorflow/issues/14886#issuecomment-352934112
I am using a DNN provided by tflearn to learn from some data. My data variable has a shape of (6605, 32) and my labels data has a shape of (6605,) which I reshape in the code below to (6605, 1)...
# Target label used for training
labels = np.array(data[label], dtype=np.float32)
# Reshape target label from (6605,) to (6605, 1)
labels = tf.reshape(labels, shape=[-1, 1])
# Data for training minus the target label.
data = np.array(data.drop(label, axis=1), dtype=np.float32)
# DNN
net = tflearn.input_data(shape=[None, 32])
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 1, activation='softmax')
net = tflearn.regression(net)
# Define model.
model = tflearn.DNN(net)
model.fit(data, labels, n_epoch=10, batch_size=16, show_metric=True)
This gives me a couple of errors, the first is...
tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape must be rank 1 but is rank 2 for 'strided_slice' (op: 'StridedSlice') with input shapes: [6605,1], [1,16], [1,16], [1].
...and the second is...
During handling of the above exception, another exception occurred:
ValueError: Shape must be rank 1 but is rank 2 for 'strided_slice' (op: 'StridedSlice') with input shapes: [6605,1], [1,16], [1,16], [1].
I have no idea what rank 1 and rank 2 are, so I do not have an idea as to how to fix this issue.
In Tensorflow, rank is the number of dimensions of a tensor (not similar to the matrix rank). As an example, following tensor has a rank of 2.
t1 = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
print(t1.shape) # prints (3, 3)
Moreover, following tensor has a rank of 3.
t2 = np.array([[[1, 1, 1], [2, 2, 2]], [[3, 3, 3], [4, 4, 4]]])
print(t2.shape) # prints (2, 2, 3)
Since tflearn is build on top of Tensorflow, inputs should not be tensors. I have modified your code as follows and commented where necessary.
# Target label used for training
labels = np.array(data[label], dtype=np.float32)
# Reshape target label from (6605,) to (6605, 1)
labels =np.reshape(labels,(-1,1)) #makesure the labels has the shape of (?,1)
# Data for training minus the target label.
data = np.array(data.drop(label, axis=1), dtype=np.float32)
data = np.reshape(data,(-1,32)) #makesure the data has the shape of (?,32)
# DNN
net = tflearn.input_data(shape=[None, 32])
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 1, activation='softmax')
net = tflearn.regression(net)
# Define model.
model = tflearn.DNN(net)
model.fit(data, labels, n_epoch=10, batch_size=16, show_metric=True)
Hope this helps.