I am trying to code a method in a research paper where I have to solve a SDP. Where one of the constraint is S succeed or equal to s*s^T. Where S is a NXN matrix and s is NX1 matrix. s^T is transpose of s.
I have found that for semidefinite constraint, Both sides of a postive semidefinite cone constraint must be square matrices and affine. Here both S and s are unknown we are minimizing equation based on S and s. and S curvature is showing unknown.
n = 2
np.random.seed(1)
Q = np.random.randn(n, n)
b = np.random.randn(n,1)
S = cp.Variable((n,n))
s = cp.Variable((n,1))
objective = cp.Minimize(cp.trace(Q#S) + 2*b.transpose()#s)
constraints = [cp.trace(S) - one.transpose()#s <= 0, S >> s#s.T]
prob = cp.Problem(objective, constraints)
print("Optimal value", prob.solve())
print("Optimal status", prob.status)
print(s.value) # A numpy ndarray.
This is the ERROR that I am getting
File "/home/mtech0/18CS60R64/cvxpy/SDP_test.py", line 45, in <module>
print("Optimal value", prob.solve())
File "/home/mtech0/18CS60R64/anaconda3/envs/mtp/lib/python3.6/site-packages/cvxpy/problems/problem.py", line 289, in solve
return solve_func(self, *args, **kwargs)
File "/home/mtech0/18CS60R64/anaconda3/envs/mtp/lib/python3.6/site-packages/cvxpy/problems/problem.py", line 567, in _solve
self._construct_chains(solver=solver, gp=gp)
File "/home/mtech0/18CS60R64/anaconda3/envs/mtp/lib/python3.6/site-packages/cvxpy/problems/problem.py", line 510, in _construct_chains
raise e
File "/home/mtech0/18CS60R64/anaconda3/envs/mtp/lib/python3.6/site-packages/cvxpy/problems/problem.py", line 499, in _construct_chains
construct_intermediate_chain(self, candidate_solvers, gp=gp)
File "/home/mtech0/18CS60R64/anaconda3/envs/mtp/lib/python3.6/site-packages/cvxpy/reductions/solvers/intermediate_chain.py", line 56, in construct_intermediate_chain
raise DCPError("Problem does not follow DCP rules." + append)
DCPError: Problem does not follow DCP rules.
Related
I merged a Vgg model and a Resnet model. The merged model will be used to extract features from frames of videos. The model is merged correctly, but it shows "AssertionError: Exception encountered when calling layer" while extracting features from frames. I am not finding any mistakes.
The code for extracting features from frames of video is mentioned below
def prepare_all_videos(df, root_dir):
num_samples = len(df)
video_paths = df["video_name"].values.tolist()
##take all classlabels from train_df column named 'tag' and store in labels
labels = df["tag"].values
#convert classlabels to label encoding
labels = label_processor(labels[..., None]).numpy()
# `frame_masks` and `frame_features` are what we will feed to our sequence model.
# `frame_masks` will contain a bunch of booleans denoting if a timestep is
# masked with padding or not.
frame_masks = np.zeros(shape=(num_samples, MAX_SEQ_LENGTH), dtype="bool")
frame_features = np.zeros(shape=(num_samples, MAX_SEQ_LENGTH, NUM_FEATURES), dtype="float32")
# For each video.
for idx, path in enumerate(video_paths):
# Gather all its frames and add a batch dimension.
frames = load_video(os.path.join(root_dir, path))
frames = frames[None, ...]
# Initialize placeholders to store the masks and features of the current video.
temp_frame_mask = np.zeros(shape=(1, MAX_SEQ_LENGTH,), dtype="bool")
temp_frame_features = np.zeros(
shape=(1, MAX_SEQ_LENGTH, NUM_FEATURES), dtype="float32"
)
# Extract features from the frames of the current video.
for i, batch in enumerate(frames):
video_length = batch.shape[0]
length = min(MAX_SEQ_LENGTH, video_length)
for j in range(length):
temp_frame_features[i, j, :] = feature_extractor.predict(
batch[None, j, :]
)
temp_frame_mask[i, :length] = 1 # 1 = not masked, 0 = masked
frame_features[idx,] = temp_frame_features.squeeze()
frame_masks[idx,] = temp_frame_mask.squeeze()
return (frame_features, frame_masks), labels
train_data, train_labels = prepare_all_videos(train_df, "train")
test_data, test_labels = prepare_all_videos(test_df, "test")
print(f"Frame features in train set: {train_data[0].shape}")
print(f"Frame masks in train set: {train_data[1].shape}")
print(f"train_labels in train set: {train_labels.shape}")
print(f"test_labels in train set: {test_labels.shape}")
The error shows
AssertionError Traceback (most recent call last)
<ipython-input-86-ae247cc8c7f3> in <module>
43
44
---> 45 train_data, train_labels = prepare_all_videos(train_df, "train")
46 test_data, test_labels = prepare_all_videos(test_df, "test")
47
2 frames
/usr/local/lib/python3.8/dist-packages/keras/engine/training.py in tf__predict_function(iterator)
13 try:
14 do_return = True
---> 15 retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
16 except:
17 do_return = False
AssertionError: in user code:
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2137, in predict_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2123, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2111, in run_step **
outputs = model.predict_step(data)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 2079, in predict_step
return self(x, training=False)
File "/usr/local/lib/python3.8/dist-packages/keras/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/usr/local/lib/python3.8/dist-packages/keras/engine/functional.py", line 679, in _run_internal_graph
assert x_id in tensor_dict, "Could not compute output " + str(x)
AssertionError: Exception encountered when calling layer 'merged_model' (type Functional).
Could not compute output KerasTensor(type_spec=TensorSpec(shape=(None, 2049), dtype=tf.float32, name=None), name='concatenated_layer/concat:0', description="created by layer 'concatenated_layer'")
Call arguments received by layer 'merged_model' (type Functional):
• inputs=tf.Tensor(shape=(None, 224, 224, 3), dtype=float32)
• training=False
• mask=None
The main error is in following line
temp_frame_features[i, j, :] = feature_extractor.predict(
batch[None, j, :]
)
Please let me know where am I going wrong? I need a solution as soon as possible.
I downloaded https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment model to my local pc.
When I pull the model from the website it works perfectly fine but it gave me tensor mismatch error on local.
`self.MODEL = "C:/Users/metehan/project1/MLTools/twitter-roberta-base-sentiment"
self.model = AutoModelForSequenceClassification.from_pretrained(self.MODEL)
self.tokenizer = AutoTokenizer.from_pretrained(self.MODEL)
self.labels = ['Negative', 'Neutral', 'Positive']`
Vocabulary sizes of model and tokenizer are the same and I don't use GPU so model, tokenizer and inputs are at the same location.
`encoded_tweet = self.tokenizer(eng_tweet, return_tensors='pt')
output = self.model(**encoded_tweet)
scores = output[0][0].detach().numpy()
scores = softmax(scores)
max_value = max(scores)`
(base) C:\Users\metehan\project1>python test.py
Traceback (most recent call last):
File "C:\Users\metehan\project1\MLTools\analyze_tweets.py", line 34, in analyze
output = self.model(**encoded_tweet)
File "C:\Users\metehan\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\metehan\AppData\Roaming\Python\Python39\site-packages\transformers\models\roberta\modeling_roberta.py", line 1206, in forward
outputs = self.roberta(
File "C:\Users\metehan\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\metehan\AppData\Roaming\Python\Python39\site-packages\transformers\models\roberta\modeling_roberta.py", line 814, in forward
buffered_token_type_ids_expanded = buffered_token_type_ids.expand(batch_size, seq_length)
RuntimeError: The expanded size of the tensor (685) must match the existing size (514) at non-singleton dimension 1. Target sizes: [1, 685]. Tensor sizes: [1, 514]
I tried adding padding and truncation to tokenizer but an index error has occured. Also adding tokenizer a max length didn't work.
Any idea how to fix this?
I have a rather simple program using dask:
import dask.array as darray
import numpy as np
X = np.array([[1.,2.,3.],
[4.,5.,6.],
[7.,8.,9.]])
arr = darray.from_array(X)
arr = arr[:,0]
a = darray.min(arr)
b = darray.max(arr)
quantiles = darray.linspace(a, b, 4)
print(np.array(quantiles))
Running this program results in an error like this:
Traceback (most recent call last):
File "discretization.py", line 12, in <module>
print(np.array(quantiles))
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/array/core.py", line 1341, in __array__
x = np.array(x)
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/array/core.py", line 1341, in __array__
x = np.array(x)
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/array/core.py", line 1341, in __array__
x = np.array(x)
[Previous line repeated 325 more times]
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/array/core.py", line 1337, in __array__
x = self.compute()
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/base.py", line 166, in compute
(result,) = compute(self, traverse=False, **kwargs)
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/base.py", line 434, in compute
dsk = collections_to_dsk(collections, optimize_graph, **kwargs)
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/base.py", line 220, in collections_to_dsk
[opt(dsk, keys, **kwargs) for opt, (dsk, keys) in groups.items()],
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/base.py", line 220, in <listcomp>
[opt(dsk, keys, **kwargs) for opt, (dsk, keys) in groups.items()],
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/array/optimization.py", line 42, in optimize
dsk = optimize_blockwise(dsk, keys=keys)
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/blockwise.py", line 547, in optimize_blockwise
out = _optimize_blockwise(graph, keys=keys)
File "/Users/zhujun/job/adf/local_training/venv/lib/python3.7/site-packages/dask/blockwise.py", line 572, in _optimize_blockwise
if isinstance(layers[layer], Blockwise):
File "/anaconda3/lib/python3.7/abc.py", line 139, in __instancecheck__
return _abc_instancecheck(cls, instance)
RecursionError: maximum recursion depth exceeded in comparison
Python is version 3.7.1 and dask is version 2.15.0.
What is wrong with this program?
Thanks in advance.
linspace does not (yet) accept lazy inputs from other dask things, you need real numbers. Use compute to materialize these numbers as follows:
a, b = dask.compute(darray.min(arr), darray.max(arr))
quantiles = darray.linspace(a, b, 4)
With either one of these package combinations:
dask==2.15.0
numpy<1.16.0
toolz==0.9.0
dask==2.16.0
numpy<1.17.0
toolz==0.9.0
The following program can be executed without an issue:
import dask.array as darray
import numpy as np
X = np.array([[1.,2.,3.],
[4.,5.,6.],
[7.,8.,9.]])
arr = darray.from_array(X)
arr = arr[:,0]
a = darray.min(arr)
b = darray.max(arr)
q0 = darray.linspace(a, b, 4)
print(np.array(q0))
The key in the above package lists is numpy. Newer versions of numpy may cause an error.
As #mdurant suggested, the implementation of linspace does not yet accept lazy inputs; hence the fact that these combinations of packages work might be actually an coincidence.
I will leave this question open until I fully understand what is happening here.
So this problem occurs for in the context of a larger project, but I've assembled a minimal working example. Consider the following:
input_1 = Input((5,))
hidden_a = Dense(2)(input_1)
hidden_b = Dense(2)(input_1)
m1 = Model(input_1, [hidden_a, hidden_b])
input_2 = Input((2,))
output = Dense(1)(input_2)
m2 = Model(input_2, output)
m3 = Model(input_1, m2(m1(input_1)[0]))
print(m3.summary())
m3.compile(optimizer='adam', loss='mse')
x = np.random.random(size=(10,5))
y = np.random.random(size=(10,1))
m3.fit(x,y)
My expectation is that when evaluating this network, the output of hidden_b will simply be discarded and I'll effectively have a simple feed-forward neural network that goes input_1 -> hidden_a -> input_2 -> output. Instead, I get a cryptic error:
Traceback (most recent call last):
File "test.py", line 37, in <module>
m3.fit(x,y)
File "/home/thomas/.local/lib/python3.5/site-packages/keras/engine/training.py", line 1013, in fit
self._make_train_function()
File "/home/thomas/.local/lib/python3.5/site-packages/keras/engine/training.py", line 497, in _make_train_function
loss=self.total_loss)
File "/home/thomas/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/thomas/.local/lib/python3.5/site-packages/keras/optimizers.py", line 445, in get_updates
grads = self.get_gradients(loss, params)
File "/home/thomas/.local/lib/python3.5/site-packages/keras/optimizers.py", line 80, in get_gradients
raise ValueError('An operation has `None` for gradient. '
ValueError: An operation has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.
Any idea what might be causing this? Thanks!
Update: If passing input_1 to m1 is the problem, then why does this work?
input_1 = Input((5,))
hidden_a = Dense(2)(input_1)
hidden_b = Dense(2)(input_1)
def sampling (args):
hidden_a, hidden_b = args
return hidden_a + hidden_b
z = Lambda(sampling)([hidden_a, hidden_b])
m1 = Model(input_1, [hidden_a, hidden_b, z])
input_2 = Input((2,))
output = Dense(1)(input_2)
m2 = Model(input_2, output)
m3 = Model(input_1, m2(m1(input_1)[2]))
m3.compile(optimizer='adam', loss='mse')
x = np.random.random(size=(10,5))
y = np.random.random(size=(10,1))
m3.fit(x,y)
You're passing an input to model 1 that is already the input of model 1.
m3 = Model(input_1, m2(m1.outputs[0]))
I am currently developing a neural network, and I got all the data and I got the code to the point that an image is being fed to the CNN for training. However, in the training process, for the first image an error pops up with the following code.
def convolutional_neural_network(x):
weights = {'W_conv1':tf.Variable(tf.random_normal([5,5,1,32])),
'W_conv2':tf.Variable(tf.random_normal([5,5,32,64])),
'W_fc':tf.Variable(tf.random_normal([7*7*64,1024])),
'out':tf.Variable(tf.random_normal([1024, n_classes]))}
biases = {'b_conv1':tf.Variable(tf.random_normal([32])),
'b_conv2':tf.Variable(tf.random_normal([64])),
'b_fc':tf.Variable(tf.random_normal([1024])),
'out':tf.Variable(tf.random_normal([n_classes]))}
x = tf.reshape(x, shape=[-1, 28, 28, 1])
conv1 = tf.nn.relu(conv2d(x, weights['W_conv1']) + biases['b_conv1'])
conv1 = maxpool2d(conv1)
conv2 = tf.nn.relu(conv2d(conv1, weights['W_conv2']) + biases['b_conv2'])
conv2 = maxpool2d(conv2)
fc = tf.reshape(conv2,[-1, 7*7*64])
fc = tf.nn.relu(tf.matmul(fc, weights['W_fc'])+biases['b_fc'])
fc = tf.nn.dropout(fc, keep_rate)
output = tf.matmul(fc, weights['out'])+biases['out']
print("hi")
return output
def shuffle_unison(images, labels):
shuffleLabel = []
shuffleImage = []
shuffleVector = []
for i in range(0, len(images)-1):
shuffleVector.append(i)
random.shuffle(shuffleLabel)
for i in range(0, len(shuffleVector)-1):
shuffleImage.append(images[shuffleVector[i]])
shuffleLabel.append(labels[shuffleVector[i]])
return shuffleImage, shuffleLabel
def train_neural_network(x):
prediction = convolutional_neural_network(x)
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
# step 4: Batching
with tf.Session() as sess:
init = tf.initialize_all_variables()
sess.run(init)
tf.train.start_queue_runners()
#array of strings and corresponding values
image_list, label_list = readImageLables()
for epoch in range(hm_epochs):
epoch_loss = 0
#shuffle every epoch
shuffle_image_list, shuffle_label_list = shuffle_unison(image_list, label_list)
sampleList = ['/home/sciencefair/Desktop/OrchardData/MachineLearningTesting/RottenOranges/result1.jpg']
for i in range(0,7683):
#filename_queue = tf.train.string_input_producer(sampleList)
file_contents = tf.read_file(shuffle_image_list[i])
image = tf.image.decode_jpeg(file_contents, channels=1)
resized_image = tf.image.resize_images(image, [28,28])
#image_batch, label_batch = tf.train.batch([resized_image, shuffle_label_list[i]], batch_size=batch_size) # does train.batch take individual images or final tensors
#if(i>batch_size):
#print(label_batch.eval())
a = tf.reshape(resized_image,[1, 784])
print(a.eval())
_, c = sess.run([optimizer, cost], feed_dict={x: tf.reshape(resized_image,[1, 784]).eval(), y: shuffle_label_list[i]})
epoch_loss += c
print("ok")
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
sess.close()
The stack trace looked like this
Caused by op 'Slice_1', defined at:
File "revisednet.py", line 128, in <module>
train_neural_network(x)
File "revisednet.py", line 87, in train_neural_network
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_ops.py", line 670, in softmax_cross_entropy_with_logits
labels = _flatten_outer_dims(labels)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_ops.py", line 472, in _flatten_outer_dims
array_ops.shape(logits), [math_ops.sub(rank, 1)], [1])
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/array_ops.py", line 431, in slice
return gen_array_ops._slice(input_, begin, size, name=name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2234, in _slice
name=name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 749, in apply_op
op_def=op_def)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2380, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1298, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Expected begin[0] == 0 (got -1) and size[0] == 0 (got 1) when input.dim_size(0) == 0
[[Node: Slice_1 = Slice[Index=DT_INT32, T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](Shape_2, Slice_1/begin, Slice_1/size)]]
This error seems to originate from the data causing some confliction with the softmax function. However I have absolutely no idea what is causing this problem.
I followed this tutorial: Sentdex,
First pass through Data w/ 3D ConvNet
to build a 3D CNN and got the same error as yours here.
This error occurs because the dimension of the label vector of my input data (for example, the location of the first label vector in Sentdex's train data is train_data[0][1]) should be the same number as n_classes which in the tutorial is 2.
In my wrong try, I just use a binary value 0 or 1 to represent it, whose dimension is 1 where should be 2. So the tf.nn.softmax_cross_entropy_with_logits() function was confused by the wrong size of label vector.
Try expand your label vectors' dimension to be equal to your n_classes.