I'm running a training code using pyhtorch and numpy.
This is the plot_example function:
def plot_example(low_res_folder, gen):
files=os.listdir(low_res_folder)
gen.eval()
for file in files:
image=Image.open("test_images/" + file)
with torch.no_grad():
upscaled_img=gen(
config1.both_transform(image=np.asarray(image))["image"]
.unsqueeze(0)
.to(config1.DEVICE)
)
save_image(upscaled_img * 0.5 + 0.5, f"saved/{file}")
gen.train()
The problem I have is that the unsqueeze attribute raises the error:
File "E:\Downloads\esrgan-tf2-masteren\modules\train1.py", line 58, in train_fn
plot_example("test_images/", gen)
File "E:\Downloads\esrgan-tf2-masteren\modules\utils1.py", line 46, in plot_example
config1.both_transform(image=np.asarray(image))["image"]
AttributeError: 'numpy.ndarray' object has no attribute 'unsqueeze'
The network is GAN network and gen() represents the Generator.
Make sure image is a tensor in the shape of [batch size, channels, height, width] before entering any Pytorch layers.
Here you have
image=np.asarray(image)
I would remove this numpy conversion and keep it a torch.tensor.
Or if you really want it to be a numpy array, then right before it enters your generator make sure to use torch.from_numpy() as shown in this documentation on your numpy image before it gets unsqueezed: https://pytorch.org/docs/stable/generated/torch.from_numpy.html
This function is ofcourse an alternative if you don't want to get rid of that original conversion.
Sarthak Jain
Related
I want to train my BERT NER model on colab. But following error occurs
Code:
tr_logits = tr_logits.detach().cpu().numpy()
tr_label_ids = torch.masked_select(b_labels, (preds_mask == 1))
tr_batch_preds = np.argmax(tr_logits[preds_mask.squeeze()], axis=1)
tr_batch_labels = tr_label_ids.to(device).numpy()
tr_preds.extend(tr_batch_preds)
tr_labels.extend(tr_batch_labels)
Error:
Using TensorFlow backend.
Saved standardized data to ./data/en/combined/train_combined.txt.
Saved standardized data to ./data/en/combined/dev_combined.txt.
Saved standardized data to ./data/en/combined/test_combined.txt.
Constructed SentenceGetter with 25650 examples.
Constructed SentenceGetter with 8934 examples.
Loaded training and validation data into DataLoaders.
Initialized model and moved it to cuda.
Initialized optimizer and set hyperparameters.
Epoch: 0% 0/5 [00:00<?, ?it/s]Starting training loop.
Epoch: 0% 0/5 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/content/FYP_Presentation/python/main.py", line 102, in <module>
valid_dataloader,
File "/content/FYP_Presentation/python/utils/main_utils.py", line 431, in train_and_save_model
tr_batch_preds = torch.max(tr_logits[preds_mask.squeeze()], axis=1)
File "/usr/local/lib/python3.6/dist-packages/torch/tensor.py", line 412, in __array__
return self.numpy()
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
How would I solve this issue?
In the first line of your code, tr_logits = tr_logits.detach().cpu().numpy() already turns tr_logits into a numpy array. In the line that raises the error:
tr_batch_preds = torch.max(tr_logits[preds_mask.squeeze()], axis=1)
the first thing for the program to do is to evaluate tr_logits[preds_mask.squeeze()]. Now that tr_logits is numpy array, its index preds_mask must also be numpy array. So the programs calls preds_mask.numpy() to change it to a numpy array. However, it is on GPU and hence the error.
I'd suggest using either numpy arrays or pytorch tensors all the way in one program, not alternatively .
I'm trying to convert input_image which is a tensor to numpy array.Following the already answered questions here and several others that suggested to use input_image.eval() or equivalently sess.run() for this conversion, I did the same, but it throws an error and apparently expects a feed_dict value for the sess.run(). But since here I'm not trying to run an operation dependent on unknown values, I don't see the need for the feed_dict here because all I'm doing here is just conversion.
Besides, just so as to check I also tried converting a tf.constant([1,2,3]) value right above it using the same method and it got successfully compiled despite its data type being the same as input_image. Here's my code which is the part of larger script:
def call(self, x):
input_image = Input(shape=(None, None, 3))
print(input_image.shape)
print(type(tf.constant([1,2,3])))
print(type(input_image))
print(type(K.get_session().run(tf.constant([1,2,3]))))
print(type(K.get_session().run(input_image)))
and here's the error:
(?, ?, ?, 3)
<class 'tensorflow.python.framework.ops.Tensor'>
<class 'tensorflow.python.framework.ops.Tensor'>
<class 'numpy.ndarray'>
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
return fn(*args)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
target_list, run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,?,?,3]
[[{{node input_1}}]]
[[input_1/_1051]]
(1) Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,?,?,3]
[[{{node input_1}}]]
0 successful operations.
0 derived errors ignored.
I wonder why the former would work and the latter won't.
There is no such thing as "converting" a symbolic tensor to a numpy array, as the latter cannot hold the same kind of information as the former.
When you use eval() or session.run(), what you are doing is evaluating a symbolic expression to get a numerical result, which is a numpy array, but this is not a conversion. Evaluating an expression might or might not require additional input data (that's what the feed_dict is for), depending on the expression.
Evaluating a constant (tf.constant) does not require any input data, but evaluating your other expression does require the input data, so you cannot "convert" this to a numpy array.
Just adding to (or elaborating on) what #MatiasValdenegro said,
TensorFlow follows something called graph execution (or define-then-run). In other words, when you write a TensorFlow program it defines something called a data-flow graph which shows how the operations you defined are related to each other. And then you execute bits and pieces of that graph depending on the results you're after.
Let's consider two examples. (I am switching to a simple TensorFlow program instead of Keras bits as it makes things more clear - After all K.get_session() returns a Session object).
Example 1
Say you have the following program.
import tensorflow as tf
a = tf.placeholder(shape=[2,2], dtype=tf.float32)
b = tf.constant(1, dtype=tf.float32)
c = a * b
# Wrong: This is what you're doing essentially when you do sess.run(input_image)
with tf.Session() as sess:
print(sess.run(c))
# Right: You need to feed values that c is dependent on
with tf.Session() as sess:
print(sess.run(c, feed_dict={a: np.array([[1,2],[2,3]])}))
Whenever a resulting tensor (e.g. c) is dependent on a placeholder you cannot execute it and get the result without feeding values to all the dependent placeholders.
Example 2
When you define a tf.constant(1) this is not dependent on anything. In other words you don't need a feed_dict and can directly run eval() or sess.run() on it.
Update: Further explanation on why you need a feed_dict for input_image
TLDR: You need a feed_dict because your resulting Tensor is produced by an Input layer.
Your input_image is basically the resulting tensor you get by feeding something to the Input layer. Usually in Keras, you are not exposed to the internal placeholder level details. But you would do that via using model.fit() or model.evaluate(). You can see that Keras Input layer in fact uses a placeholder by analysing this line.
Hope I made my point clear that you do need to feed in a value to the placeholder to successfully evaluate the output of an Input layer. Because that basically holds a placeholder.
Update 2: How to feed to your Input layer
So, appears you can use feed_dict with Keras Input layer in the following manner. Instead of defining shape argument you straight away pass a placeholder to the tensor argument, which will bypass the internal placeholder creation in the layer.
from tensorflow.keras.layers import InputLayer
import numpy as np
import tensorflow.keras.backend as K
x = tf.placeholder(shape=[None, None, None, 3], dtype=tf.float32)
input_image = Input(tensor=x)
arr = np.array([[[[1,1,1]]]])
print(arr.shape)
print(K.get_session().run(input_image, feed_dict={x: arr}))
I am training a neural network and a part of my code has returned the following error:
def plot_confusion_matrix(truth,
predictions,
classes,
normalize=False,
save=False,
cmap=plt.cm.Oranges,
path="confusion_matrix.png"):
acc = (np.array(truth) == np.array(predictions))
size = float(acc.shape[0]) #error
acc = np.sum(acc.astype("int32")) / size
(...)
AttributeError: 'bool' object has no attribute 'shape'
function call
pred = pred.numpy()
plot_confusion_matrix(truth=labels.numpy(),
predictions=pred,
save=False,
path="logref_confusion_matrix.png",
classes=["forward", "left", "right"])
Where the thuth represents the labels of Y and predictions the array of prediction, both with shape 32, 3. I checked the update on numpy, ipython etc and all are updated, tried some modification, but without success.
The only reason that acc would be a boolean and not a numpy array of booleans is that you are passing in a singular value for truth and predictions. In the code you provided, there would be no error for an actual array of 32x3. Look at the rest of your code and make sure you actually pass in an array to np.array() instead of singular values.
I was wondering if I can build an image resize module in Pytorch that takes a torch.tensor of 3*H*W as the input and return a tensor as the resized image.
I know it is possible to convert tensor to PIL Image and use torchvision,
but I also hope to back propagate gradients from the resized image to the original image, and the following example will return such error (in PyTorch 0.4.0 on Windows 10):
import numpy as np
from torchvision import transforms
t2i = transforms.ToPILImage()
i2t = transforms.ToTensor()
trans = transforms.Compose(
t2i, transforms.Resize(size=200), i2t]
)
test = np.random.normal(size=[3, 300, 300])
test = torch.tensor(test, requires_grad=True)
resized = trans(test)
resized.backward()
print(test.grad)
Traceback (most recent call last):
File "D:/Projects/Python/PyTorch/test.py", line 41, in <module>
main()
File "D:/Projects/Python/PyTorch/test.py", line 33, in main
resized = trans(test)
File "D:\Anaconda3\envs\pytorch\lib\site-packages\torchvision\transforms\transforms.py", line 42, in __call__
img = t(img)
File "D:\Anaconda3\envs\pytorch\lib\site-packages\torchvision\transforms\transforms.py", line 103, in __call__
return F.to_pil_image(pic, self.mode)
File "D:\Anaconda3\envs\pytorch\lib\site-packages\torchvision\transforms\functional.py", line 102, in to_pil_image
npimg = np.transpose(pic.numpy(), (1, 2, 0))
RuntimeError: Can't call numpy() on Variable that requires grad. Use var.detach().numpy() instead.
It seems like I cannot "imresize" a tensor without detaching it from autograd first, but detaching it prevents me from computing gradients.
Is there a way to build a torch function/module that does the same thing as torchvision.transforms.Resize that is autograd compatiable? Any help is much appreciated!
torch.nn.functional.upsample works for me, ypa!
I just figured it out how to preserve the gradients when implementing custom loss function.
The trick is to attach your result to the dummy gradients
def custom_loss(tensor1, tensor2):
# convert tensors to PIL image, doing calculation, we have output = 0.123
grad = (tensor1 + tensor2).sum()
loss = grad - grad + output
return loss
I am learning to deal with python and lasagne. I have following installed on my pc:
python 3.4.3
theano 0.9.0
lasagne 0.2.dev1
and also six, scipy and numpy. I call net.fit(), and the stacktrace tries to call train_split(X, y, self), which, I guess, should split the samples into training set and validation set (both the inputs X as well as the outputs Y).
But there is no method like train_split(X, y, self) , there is only a float field train_split - I assume, the ratio between training and validation set sizes. Then I get following error:
Traceback (most recent call last):
File "...\workspaces\python\cnn\dl_tutorial\lasagne\Test.py", line
72, in
net = net1.fit(X[0:10,:,:,:],y[0:10])
File "...\Python34\lib\site-packages\nolearn\lasagne\base.py", line
544, in fit
self.train_loop(X, y, epochs=epochs)
File "...\Python34\lib\site-packages\nolearn\lasagne\base.py", line
554, in train_loop
X_train, X_valid, y_train, y_valid = self.train_split(X, y, self)
TypeError: 'float' object is not callable
What could be wrong or missing? Any suggestions? Thank you very much.
SOLVED
in previous versions, the input parameter train_split has been a number, that was used by the same-named method. In nolearn 0.6.0, it's a callable object, that can implement its own logic to split the data. So instead of providing a float number to the input parameter train_split, I have to provide a callable instance (the default one is TrainSplit), that will be executed in each training epoch.