Based on the above data, answer the given subquestions.
Using the actual flattened feature size from previous question number 2, how many learnable
parameters (weights + bias) would a fully connected layer with 10 outputs have?
A published solution is not available for this question yet.
for transpose Convolution ).
The corresponding encoder to the above decoder downsampled an original 96×96 input via 3
stride-2 stages down to 12×12.
Based on the above data, answer the given subquestions.
What is the output height after
? The width is the same; enter one integer only.
A published solution is not available for this question yet.
for transpose Convolution ).
The corresponding encoder to the above decoder downsampled an original 96×96 input via 3
stride-2 stages down to 12×12.
Based on the above data, answer the given subquestions.
What is the output height after
? The width is the same; enter one integer only.
A published solution is not available for this question yet.
for transpose Convolution ).
The corresponding encoder to the above decoder downsampled an original 96×96 input via 3
stride-2 stages down to 12×12.
Based on the above data, answer the given subquestions.
Which layer is responsible for the decoder failing to reach the target 96×96 output, and why?
6406537408147.
, because its kernel size is too small.
6406537408148.
, because it uses the wrong number of input channels.
6406537408149.
, because it uses
instead of
, so it fails to double the
spatial resolution.
6406537408150.
None of the layers — the decoder already produces a 96×96 output.
A published solution is not available for this question yet.
for transpose Convolution ).
The corresponding encoder to the above decoder downsampled an original 96×96 input via 3
stride-2 stages down to 12×12.
Based on the above data, answer the given subquestions.
Suppose instead the decoder's input
had spatial size 20×20 (instead of 12×12). After applying
the correction identified in previous question, what would the final output height be? The width is
the same; enter one integer only.
A published solution is not available for this question yet.
Consider an input of size **48×48×24** (24 channels), a standard
, and the
module above. Ignore bias
terms throughout, and assume spatial size is preserved (48×48 output) in both cases.
Based on the above data, answer the given subquestions.
How many learnable parameters does the standard
have?
A published solution is not available for this question yet.
Consider an input of size **48×48×24** (24 channels), a standard
, and the
module above. Ignore bias
terms throughout, and assume spatial size is preserved (48×48 output) in both cases.
Based on the above data, answer the given subquestions.
How many total learnable parameters does
have (depthwise +
pointwise combined)?
A published solution is not available for this question yet.
Consider an input of size **48×48×24** (24 channels), a standard
, and the
module above. Ignore bias
terms throughout, and assume spatial size is preserved (48×48 output) in both cases.
Based on the above data, answer the given subquestions.
What is the parameter compression ratio (standard ÷ depthwise-separable), rounded to 2 decimal
places?
A published solution is not available for this question yet.
Consider an input of size **48×48×24** (24 channels), a standard
, and the
module above. Ignore bias
terms throughout, and assume spatial size is preserved (48×48 output) in both cases.
Based on the above data, answer the given subquestions.
Which of the following statements about
are correct?
6406537408155.
The depthwise layer uses
, so each input channel is convolved
independently.
6406537408156.
The pointwise 1×1 layer learns combinations across the depthwise-filtered
channels.
6406537408157.
The pointwise 1×1 layer operates independently on every channel and
therefore cannot mix channel information.
6406537408158.
The parameter saving relative to a standard convolution depends on the
kernel size and channel counts.
A published solution is not available for this question yet.
architecture itself has already been corrected so that its classifier input size
matches the feature output. Focus only on the training/checkpoint/inference pipeline below.
Based on the above data, answer the given subquestions.
Which of the following statements correctly identify a real bug in the given code ?
6406537408136.
is never called, so gradients accumulate across
batches instead of being reset before each step.
6406537408137.
saves the full model object, but the reload code
calls
, which expects a state dict rather than a
model instance.
6406537408138.
is never moved to
, so
will raise a device-
mismatch error whenever
is a GPU.
6406537408139.
is the wrong loss function for a 10-class
classification problem.
A published solution is not available for this question yet.
architecture itself has already been corrected so that its classifier input size
matches the feature output. Focus only on the training/checkpoint/inference pipeline below.
Based on the above data, answer the given subquestions.
Suppose the device-mismatch bug is fixed, but
is still never called before
inference. Given that
uses BatchNorm, what is the most likely consequence?
6406537408140.
No effect — BatchNorm behaves identically in train and eval mode.
6406537408141.
BatchNorm continues to use statistics from the current inference batch
instead of the stored running statistics, so predictions can differ from proper evaluation-mode
inference and can depend on batch composition.
6406537408142.
The model automatically switches to eval mode whenever
is used.
6406537408143.
The prediction will be correct but computed twice as slowly.
A published solution is not available for this question yet.
architecture itself has already been corrected so that its classifier input size
matches the feature output. Focus only on the training/checkpoint/inference pipeline below.
Based on the above data, answer the given subquestions.
In the fully corrected pipeline, if
yields 18 batches per epoch over 4 epochs, how
many total times should
be called?
A published solution is not available for this question yet.
A convolutional layer receives a feature map with **24 input channels** and applies **40 filters**, each
of spatial size **5 × 5**. Following the "generic level of CNN" view (a filter spans all input channels),
calculate the total number of **weights (excluding bias)** in this layer.
A published solution is not available for this question yet.
A convolutional layer is applied to a **48 × 48** input using a **5 × 5** filter with **zero-padding of 2** and
**stride 2**. Using the standard convolution output-size formula, calculate the **output width (one**
**spatial dimension)**. The height is the same; enter one integer only.
A published solution is not available for this question yet.
The final classification head applies a **softmax** over the pre-activation scores (logits). For a 3-class
problem, the logits produced for a particular image are **[2, 1, 0]**. Compute the softmax **probability**
**assigned to the first class** (round to 2 decimal places).
A published solution is not available for this question yet.
Following the VGG design philosophy of replacing a single large-kernel convolution with a cascade
of small **3 × 3, stride-1** convolutions, how many such 3 × 3 layers must be **stacked** so that the
resulting stack has the same effective (one-dimensional) receptive field as a **single 13 × 13**
**convolution**
A published solution is not available for this question yet.
A YOLOv1-style detector divides the input image into an **S = 16** grid. Each grid cell predicts **B = 2**
bounding boxes (each with
) and a single set of class scores over **C =**
**20** classes.
Compute the **total number of scalar values** in the final output tensor of the network.
A published solution is not available for this question yet.
The decoder of a depth-estimation network upsamples feature maps using a **transposed**
**convolution** ("up-convolution") with **kernel size 4, stride 2, and padding 1**. If the input feature
map has spatial size **24 × 24**, what is the output height? The width is the same; enter one integer
only.
A published solution is not available for this question yet.
In the original U-Net used for dense prediction (and adaptable to depth estimation), each encoder
stage applies **two successive 3×3 convolutions with no padding (stride 1)**, followed by a **2×2**
**max-pooling with stride 2**. If the input feature map to one such encoder stage has spatial size
**132 × 132**, what is the output height of the feature map **after both convolutions and the max-**
**pooling** of that stage? The width is the same; enter one integer only.
A published solution is not available for this question yet.
The SRGAN discriminator is a stack of **8 convolutional layers**, all using **3 × 3 kernels with**
**padding 1**, and strides alternating as **s = 1, 2, 1, 2, 1, 2, 1, 2** across the eight layers (the stride-1
layers preserve spatial size; the stride-2 layers downsample).
If the input image is **128 × 128**, what is the output height of the feature map **after the last (8th)**
**convolutional layer**, just before the dense layers? The width is the same; enter one integer only.
A published solution is not available for this question yet.
Efficient restoration networks (e.g., LaKDNet) replace standard convolutions with **depth-wise**
**separable convolutions** (a depth-wise convolution followed by a point-wise 1×1 convolution).
An input feature map of size **24 × 24 × 24** (24 channels) is processed by a depth-wise separable
convolution that uses **3 × 3** depth-wise kernels and produces **48 output channels**, with stride 1
and padding 1 (so the spatial size is preserved).
Calculate the **total number of multiplications** for the full depth-wise separable operation (depth-
wise + point-wise). Give the answer in millions (e.g., if 1,234,567 write 1.23).
A published solution is not available for this question yet.
Which of the following statements about the **ResNet** architecture and its standard training recipe
are **correct**?
6406537408163.
Dropout is applied after every residual block as the primary regularizer.
6406537408164.
Batch Normalization is applied after every convolutional layer.
6406537408165.
The identity shortcut connection lets gradients bypass the weight layers,
helping mitigate vanishing gradients in very deep networks.
6406537408166.
A global average pooling layer is used after the final convolutional stage, so
the network has no large fully-connected layers other than the final classifier (FC-1000).
A published solution is not available for this question yet.
Which of the following statements about the **GoogLeNet / Inception** architecture are correct?
6406537408167.
A naive Inception module concatenates parallel branch outputs along the
channel dimension; its output depth is determined by the number of output filters/channels in the
branches, not by the filter sizes.
6406537408168.
1×1 "bottleneck" convolutions are inserted before the expensive 3×3 and 5×5
convolutions to reduce input depth and cut down the number of operations.
6406537408169.
The final classifier relies on two large fully-connected layers (like AlexNet's
FC6/FC7) which account for most of GoogLeNet's parameters.
6406537408170.
Auxiliary classifiers are attached to intermediate layers to inject additional
gradient signal and combat vanishing gradients during training.
A published solution is not available for this question yet.
Which of the following statements about **evaluating object detectors with mAP** are correct?
6406537408175.
mAP measures **only** classification accuracy and is **independent** of how well
the boxes are localized.
6406537408176.
IoU is defined as the **area of overlap divided by the area of union** between
the predicted box and the ground-truth box.
6406537408177.
A prediction with IoU **above** the threshold and the **correct class** is a True
Positive; one with IoU at or below the threshold (or matching no ground-truth box) is a False
Positive.
6406537408178.
Average Precision (AP) for a class is the **area under its Precision–Recall**
**curve**, and mAP is the **mean of AP over all classes**.
A published solution is not available for this question yet.
Regarding the **channel-attention module in CBAM**, which of the following are correct?
6406537408190.
It exploits the **inter-channel** relationship of features, learning "what" is
meaningful by re-weighting feature channels.
6406537408191.
It produces a **spatial** attention map of size H × W × 1 that highlights where to
focus, discarding all channel information.
6406537408192.
The spatial dimensions of the input feature map are squeezed using **both**
**average-pooling and max-pooling**, producing two channel descriptors.
6406537408193.
The pooled descriptors are passed through a **shared MLP**, combined, and a
sigmoid produces the channel attention weights that rescale the input feature map.
A published solution is not available for this question yet.
In the **multi-scale deep network** for single-image depth estimation (Eigen et al.), the architecture
is split into a **coarse network** and a **fine network**. Which statement best explains their respective
roles?
6406537408184.
The coarse network uses a large receptive field (via deeper layers and fully-
connected layers) to predict the global scene depth, while the fine network refines this prediction
locally using input-image details.
6406537408185.
The fine network predicts the global scene structure, and the coarse network
only sharpens edges.
6406537408186.
Both networks are architecturally identical and their outputs are simply
averaged (ensembled).
6406537408187.
The coarse network processes each pixel independently and therefore ignores
global scene context.
A published solution is not available for this question yet.
