I did not have any choice except asking here. I have a lot of difficulties for a long time. I have not been to observe any output from FCN32 :(
I trained FCN32 on my data from scratch and always getting a black image. I added gaussian with std= 0.01 initialization for convolutional layers. But still I get black image.
I tried to add weighted loss layers. However, I was not successful to add it correctly. I am not good at python and c++.
My questions:
Is there any correct PR that it can easily include this layer?
My data has 5 classes that the proportion of classes differ from each other in different images. How can I create these weight matrices for each image?
I really appreciate any help. Please share if you know any resource/link/ or if I can get it from other networks' repositories.
Related
I'm new to deep learning, so maybe this is a silly question...
Do any adjustments need to be made for applying Grad-CAM on CNNs that use a Global Average Pooling (GAP) layer right before fully connected ones?
I understand that the GAP layer aggregates the activations of an intermediate layer in order to produce a compact representation of the image, removing information regarding the features location. Is this an obstacle to grad-cam backpropagation?
I imagine that for a CNN that uses, for example, a Max Pooling layer followed by a Flatten layer, o Grad-CAM is capable of retriving the exact location of the relevant features.
I'm sorry if it is a silly doubt, but I couldn't find the answer for it anywhere.
Thanks in advance!
I have been experimenting with grad-cam with some VGGNets and ResNets in different tasks. It could be something in my head, but apparently ResNet tends to highlight larger regions in the image. Both models classify correctly, but the ResNet activation map usually highlights a larger area.
Even in the original Grad-CAM paper, this also happens, as shown below. However, I can't find any comments about it, I would like to know why.
Grad-CAM for VGGNet
Grad-CAM for ResNet
Currently trying yolov5 with custom synthetic data. The dataset we've created consists of 8 different objects. Each object has a minimum of 1500 pictures/labels, where the pictures are split 500/500/500 of normal/fog/distractors around object. Sample images from the dataset is in the first imgur link. The model is not trained from scratch, but from yolov5 standard .pt.
So far we've tried:
Adding more data (from 300 images per object, to 4500)
Creating more complex data (distractors on/around objects)
Running multiple runs of training
Trained with network size small, medium, large, xlarge
Different batch size between 4-32 (depending on model size)
Everything so far has resulted in good/great detection on synthetic data, but completely off when used on real-life data.
Examples: Thinks that the whole pictures of unrelated objects is a paperbox, walls are pallets, etc. Quick sample images in the last imgur link.
Anyone got clues for how to improve the training or data to be better suited for real life detection? Or how to better interpret the results? I don't understand how the model draws the conclusion that a whole picture, with unrelated objects, is a box/pallet.
Results from training uploaded to imgur:
https://imgur.com/a/P0TQeBl
Example on real life data:
https://imgur.com/a/SGY7w8w
There are couple of things to improve results.
After training your model with synthetic data, fine tune your model with real training data, with a smaller learning rate (1/10th maybe). This will reduce the gap between synthetic and real life images. In some cases rather than fine tuning, training the model with mixed (synthetic+real) produces better results.
Generate images structurally similar to real life examples. For example, put humans inside forklifts, or pallets or barrels on forks, etc. Models learn from it.
Randomize the texture on items that you want to detect. Models tend to focus on textures for detection. By randomizing textures, with lots of variability including mon natural occurrences, you force model to learn to identify objects not based on its textures. Although, texture of an object sometimes is a good identifier, synthetic data suffers from not replicating that feature good enough, hence the domain gap, so you reduce its impact on model decision.
I am not sure whether the screenshot accurately represent your data generation distribution, if so, you have to randomize the angles of objects, sizes and occlusion amounts more.
Use objects that you don’t want to detect but will be in the images you will do inference as distractors, rather than simple shapes like spheres.
Randomize lighting more. Intensity, color, angles etc.
Increase background and ground randomization. Use hdris, there are lots of free hdris
Balance your dataset
https://imgur.com/a/LdCa8aO
Checking your results the answer is that your synthetic data is way to dissimilar to the real life data you want it to work for. Try to generate synthetic scenes that are closer to your real life counterparts and training again would clearly improve your results. That includes more realistic backgrounds and scene compositions. I don't know if your training set resembles the validation images you shared here but in case it does, try to have more objects per image, closer to the camera and add variation to their relative positions. Having just one random 3D object in the middle of an image is not going to provide good results. By the way, you are already overfitting your models, so more training images wouldn't help at this point.
I've been thinking that adding noise to an image can prevent overfitting and also "increase" the dataset by adding variations to it. I'm only trying to add some random 1s to images that has shape (256,256,3) which uses uint8 to represent its color. I don't think that can affect the visualization at all (I showed both images with matplotlib and they seems almost the same) and has only ~0.01 mean difference in the sum of their values.
But it doesn't look to have its advances. After training for a long time it's still not as good as the one doesn't use noises.
Has anyone tried to use noise for image classification tasks like this? Is it eventually better?
I wouldn't go to add noise to your data. Some papers employ input deformations during training to increase robutness and convergence speed of models. However, these deformations are statistically inefficient (not just on image but any kind of data).
You can read Intriguing properties of Neural Networks from Szegedy et al. for more details (and refer to references 9 & 13 for papers that uses deformations).
If you want to avoid overfitting, you might be interested to read about regularization instead.
Yes you may add noise to extend your dataset and avoid overfitting your training set but make sure it is random otherwise your network will take this noise as something it should learn (and that's not something you want). I wouldn't use this method first to do that, I would first rotate and/or flip my samples.
However, your network should perform better or, at least, as well as your previous network.
First thing I would check is : How do you measure your performances ? What were your performances before and after ? And did you change anything else ?
There are a couple of works that deal with this problem. Because you make the training set harder the training error will be lower, however your generalization might be better. It has been shown that adding noise can have stability effects for training Generative Adversarial Networks (Adversarial Training).
For classification tasks it is not that cut and dry. Not many works have actually dealt with this topic. The closest one is to my best knowledge is this one from google (https://arxiv.org/pdf/1412.6572.pdf), where they show the limitation of using training without noise. They do report a regularization effect, but not actual better results than using other methods.
I'm a student major in physics as well as CS. One of my tasks is to find the supernova. The discovery of supernova is tedious and tough.
Through contrast the picture now and before, then we may find some bright spot on the picture and that may be the supernova.
like this,
The picture has many noise, and there are always many ghost spot because of instability of the instruments, or other lights make the illusions.
However, the supernova has some obvious characteristics, it always show up around the fixed stars. The shape of light is circle. etc.There already some conventional methods used on that. But they don't have good performance.
So I wonder if it's worthwhile trying it on CNN.
Which kind of data can CNN do well on?
Thanks.
So I wonder if it's worthwhile trying it on CNN.
I think CNN is overkill for this problem.
Which kind of data can CNN do well on?
Data with complex localised relationships in the structure and a large number of features. You use a convolution across a local frame to learn the representation.
The problem you have is very simple. You don't have many parameters, i.e. colour is grayscale, representation of a supernova is all contained within the immediate vicinity of it's occurrence.
I think you would probably have much more success with some really simple algorithm such as:
Find all fixed stars
search for any big 'blobs' of light with specific parameters
search for any circles of light
These alone will massively reduce the computational size of the problem. From there, there are a number of ML approaches you could take.
CNNs are generally for very big data sets with highly complex non-linear relationships. This (may?) be a big data set but it is certainly not complex in this particular task.
I don't have much experience in machine learning, pattern recognition, data mining, etc. and in their underlying theory and systems.
I would like to develop an artificial model of the time it takes a human to make a move in a given Sudoku puzzle.
So what I'm looking for as an output from the machine learning process is a model that can give predictions on how long does it take for a target human to make a move in a given Sudoku situation.
Same input doesn't always map to same outcome. It takes different times for the human to make a move with the same situation, but my hypothesis is that there's a tendency in the resulting probability distribution. (My educated guess is that it is ~normal.)
I have ideas about the factors that influence the distribution (like #empty slots) but would preferably leave it to the system to figure these patterns out. Please notice, that I'm not interested in the patterns, just the model.
I can generate sample and test data easily by running sudoku puzzles and measuring the times it takes to make the moves.
What kind of learning algorithm would you suggest to use for this?
I was thinking NNs, but I'm not sure if they can have the desired property of giving weighted random outcomes for the same input.
If I understand this correctly you have an input vector of length 81, which contains 1 if the square is filled in and 0 otherwise. You want to learn a function which returns a probability distribution which models the response time of a human to that board position.
My first response would be that this is a regression problem and you should try straightforward linear regression. This will not provide you with a distribution of response times, but a single 'best-guess' response time.
I'm not clear on why you want to model a distribution of response times. However, if you really want to do want to output a distribution then it sounds like you want to look at Bayesian methods. I'm not really an expert on Bayesian inference, so I can't help you much further here.
However, I don't really think your approach is going to work because I agree with your intuition about features such as the number of empty slots being important. There are also other obvious features, such as the number of empty slots per row/column that are likely to be important. Explicitly putting these features in your representation will probably be much more successful than expecting that the learning algorithm will infer something similar on its own.
The monte carlo method seems like it would work well here but would require a stack of solutions the size of the moon to really do it. And it wouldn't give you the time per person, just the time on average.
My understanding of it, tenuous as it is, is that you have a database with a board position and the time it took a human to make the next move. At the very least you have a starting point for most moves. Even if it's not in the database you could start to calculate how long it would take to make a move based on some algorithm. Though I know you had specified you wanted machine learning to do this it might be worth segmenting the problem into something a little smaller then building on it.
If you have some guesstimate as to what influences the function (# of empty cell, etc), try to train a classifier on a vector of features, and not on the 81 cells vector (0/1 or 0..9, doesn't really matter for my argument).
I think that your claim:
we wouldn't have to necessary know the underlying patterns, the "trained patterns" in a learning system automatically encodes these sometimes quite delicate and subtle patterns inside them -- that's one of their great power
is wrong. you do have to give the network the right domain. for example, when trying to detect object in an image, working in the pixel domain is pointless. you'll only get results if you first run some feature detection to detect edges, corners, etc.
Theoretically, with enough non-linearity (in NN - enough layers in the network) it can detect such things, but in practice, I have never seen that work, without giving the classifier the right features to work with.
I was thinking NNs, but I'm not sure if they can have the desired property of giving weighted random outcomes for the same input.
You're just trying to learn a function from 2^81 or 10^81 (or a much smaller feature space as I suggest) to R (response time between 0 and Inf) or some discretization of that. So NN and other classifiers can do that.