PyTorch Certified Associate (PTCA) 1 Prepare for the Linux Foundation PTCA Certification Exam with Practice Questions Get - https://bit.ly/4hrsdhD - ready for the Linux Foundation PyTorch Certified Associate (PTCA) Certification Exam with comprehensive practice questions designed to strengthen your knowledge and exam readiness. Use realistic practice questions to assess your understanding, identify weak areas, and focus your preparation on the key topics covered in the PTCA exam. Regular practice can help you build confidence, improve your time management, and approach the actual certification exam with greater confidence. www.vmexam.com PyTorch Certified Associate (PTCA) 1 PTCA Practice Test The PTCA (Linux Foundation PyTorch Certified Associate) certification is offered by the Linux Foundation and is designed to validate your foundational knowledge and practical understanding of PyTorch. If you are preparing for the PTCA Certification Exam, having the right study resources and sufficient practice can make your preparation more effective. Our PTCA Question Bank and practice exams are designed to help you become familiar with the types of questions and topics you may encounter during your certification preparation. Instead of relying only on books and theoretical study materials, you can use our PTCA practice questions to test your knowledge and measure your current level of preparation. By regularly attempting practice exams, you can identify the topics where you need improvement and dedicate more time to the areas that require additional attention. This approach allows you to understand your strengths and weaknesses while providing a structured way to review the PTCA exam syllabus. PyTorch Certified Associate (PTCA) 2 PTCA Exam Details Exam Name Linux Foundation PyTorch Certified Associate (PyTorch Associate) Exam Code PTCA Exam Price $250 USD Duration 120 minutes Number of Questions 60 Passing Score 75% Schedule Exam Linux Foundation Sample Questions Linux Foundation PTCA Sample Questions Recommended Practice PyTorch Certified Associate (PTCA) Practice Test PTCA Exam Syllabus Section Objectives Weight PyTorch Fundamentals - Core Concepts - Tensors - Training, Testing, and Using Models - Device Basics (CPU, CUDA, MPS, etc) 38% Model Development - PyTorch Neural Network (NN) Building Blocks 20% Performance & Optimization - Precision and Execution Optimization - Performance Measurement - Distributed Training 26% Data Handling - Datasets - DataLoaders - Transforms - Training Data 16% PyTorch Certified Associate (PTCA) 3 PTCA Questions and Answers Set 01. For an image classification model you want each training image converted to a tensor and then standardized per channel. Which construction correctly chains these steps in order? a) ToTensor(Normalize(mean, std)) b) Compose([Normalize(mean, std), ToTensor()]) c) Normalize(ToTensor(), mean, std) d) Compose([ToTensor(), Normalize(mean, std)]) Answer: d 02. You are choosing which per-channel mean and std to pass to Normalize in your training transform pipeline. Why is normalizing inputs a common preprocessing step? a) It increases the effective number of training samples by generating extra augmented copies of the data b) It rescales features to a comparable range, which keeps gradients well-behaved and stabilizes optimization c) It guarantees the model cannot overfit by clamping every input feature to a fixed unit range d) It converts the integer class labels into one-hot encoded target vectors for the loss Answer: b 03. You already hold your features and labels as two aligned tensors, X and y, and want to feed them to a DataLoader without writing a custom class. Which utility wraps existing tensors into a ready-to-use dataset? a) random_split(X, y) b) Compose(X, y) c) TensorDataset(X, y) d) DataLoader(X, y) Answer: c PyTorch Certified Associate (PTCA) 4 0 4. A colleague removes optimizer.zero_grad() from their training loop, keeping the forward pass, loss.backward(), and optimizer.step() each iteration. What happens as a result, and why? a) Nothing changes, because loss.backward() automatically overwrites the previous .grad values on every call, so each step still uses only the current batch. b) Gradients accumulate into .grad, so each step sums gradients across batches rather than using only the current one, corrupting the updates. c) Training halts with a runtime error, because PyTorch forbids running another backward pass while non-zero gradients from a prior iteration are still present. d) The parameters gradually stop updating, because the accumulated gradients from successive batches cancel out to a net value of zero. Answer: b 05. During evaluation a developer calls model.eval() and then runs the validation batches, but memory usage stays high and the autograd graph is still being built. Which statement best explains the situation and the fix? a) model.eval() only switches layers like Dropout and BatchNorm; it does not disable gradient tracking, so also wrap evaluation in a with torch.no_grad(): block. b) model.eval() already disables autograd, so the persistent memory must instead come from an unrelated leak in the data loader or metric accumulation. c) You must run a loss.backward() pass during validation to release the graph that eval() would otherwise leave allocated across batches. d) Switching back to model.train() during validation would disable gradient tracking and lower memory, at the cost of re-enabling Dropout. Answer: a PyTorch Certified Associate (PTCA) 5 06. In a standard PyTorch training loop, you call optimizer.step() after computing the loss and calling loss.backward(). What does optimizer.step() do? a) It resets all parameter gradients to zero so they are clean before the next iteration. b) It updates the model parameters using the gradients that were computed during backpropagation. c) It runs the forward pass over the input batch to produce the predictions the loss is computed from. d) It computes the gradients of the loss with respect to each of the model's trainable parameters. Answer: b 07. A teammate defines a classifier whose final layer produces raw logits, then writes: probs = softmax(logits, dim=1) followed by loss = criterion(probs, targets), where criterion = nn.CrossEntropyLoss(). Why is this a bug, and how should it be fixed? a) The real bug is the softmax dimension: dim=0 normalizes across the batch, so keeping the softmax but switching it to dim=1 makes the loss correct. b) The targets must also be one-hot encoded to match the softmax output, and adding that encoding aligns the shapes so the loss computes correctly. c) There is no bug here; nn.CrossEntropyLoss needs probabilities as input, so applying softmax to the logits first is exactly the required preprocessing. d) nn.CrossEntropyLoss already applies log-softmax internally, so the extra softmax double-applies it; pass the raw logits instead. Answer: d PyTorch Certified Associate (PTCA) 6 08. When implementing gradient accumulation over several mini-batches, a common mistake is forgetting one step of the loop. Which step is essential to accumulate correctly? a) Call optimizer.zero_grad() only after the accumulated optimizer.step(), not after every mini-batch. b) Move the model to the CPU in between the mini-batches so that accumulated gradient memory is freed. c) Call optimizer.zero_grad() after every single mini-batch so the gradients never overlap between steps. d) Detach the loss with .item() before you call backward() on it each iteration. Answer: a 09. A model applies an in-place ReLU (the variant ending in _) to a tensor whose original values are later needed to compute gradients during backward(). The run raises an autograd error about a value modified in place. Why does the in-place operation cause this? a) The error happens because in-place operations are forced to run on the CPU while the rest of the model runs on the GPU. b) In-place ops double the tensor's memory use, triggering an out-of-memory failure that surfaces as an autograd error. c) The in-place op overwrote a value autograd had saved for the backward pass, so the gradient can no longer be computed. d) In-place operations are always disallowed anywhere inside a model that relies on autograd for its gradients. Answer: c PyTorch Certified Associate (PTCA) 7 10. During inference you wrap the forward pass in torch.no_grad(). What does torch.no_grad() do? a) It moves the model along with all of its input tensors onto the GPU so that the forward pass runs faster. b) It permanently deletes the gradients already stored on the model's parameters. c) It switches dropout and batch-norm layers into their evaluation behavior for correct inference. d) It disables gradient tracking so autograd does not build the computation graph, saving memory and time. Answer: d Full Online Practice of PTCA Certification VMExam.com is one of the world ’ s leading certifications, Online Practice Test providers. We partner with companies and individuals to address their requirements, rendering Mock Tests and Question Bank that encourages working professionals to attain their career goals. You can recognize the weak area with our premium PTCA practice exams and help you to provide more focus on each syllabus topic covered. Start Online practice of PTCA Exam by visiting URL https://www.vmexam.com/linux-foundation/ptca-linux-foundation- pytorch-certified-associate