In the paper “Grid Long Short-Term Memory” the authors describe a translation model (section 4.4). My first impression was that this model was considered a 3-D Grid LSTM model, because it consisted of two 2-D Grids stacked on top of each other, i.e. two layers. Then, I read this: “The 3-LSTM uses two two-dimensional grids of 3-LSTM blocks for the hierarchy” and "Note that the second grid receives an input coming from the grid below at each 3-LSTM block". Does this mean that the 2-D grids, consists of 3-Dimensional LSTMs? In the introduction, they say that N-LSTM is a shorter notation for N-dimensional Grid LSTM.
This is a figure of their model:
But I'm wondering if the next figure may represent the model better based on the information above (just with fewer layers):
I'm using Tensorflow, and I have used the MultiRNNCell to stack two Grid2LSTMCells on top of each other. But now I'm thinking that I should rather use the Grid3LSTMCell.. Any comments or thoughts? :)
Related
I want to recommend an item complementary to a cart of items. So, naturally, I thought of using embeddings to represent items, and I came up to a layer of this kind in keras:
item_input = Input(shape=(MAX_CART_SIZE,), name="item_id")
item_embedding = Embedding(input_dim=NB_ITEMS+1, input_length=MAX_CART_SIZE, output_dim=EMBEDDING_SIZE, mask_zero=True)
I used masking to handle the variable size of the carts. So, the dimensions of the output tensor of this layer is MAX_CART_SIZE x EMBEDDING_SIZE. It means that there are as many different embeddings as there are potential items. In other words, a item can be encoded a different way according to its position within the cart and that's an undesirable behavior... Though, it seems that most neural networks dealing with NLP data work this way, with embeddings not associated with words but with words/indices within a phrase.
So, what would be the correct way to preserve order invariance? In other words, I'd like the cart A,B,C be stricly equivalent to the carts C,B,A or B,A,C in terms of input representation and generated output.
One way of having invariance will be done by using a Transformer architecture WITHOUT using positional embeddings. In this way, each item is encoded to an embedding, and because you do not have a positional embedding, the object embedding is the same even if it is one the first position or on the last one.
Moreover, the Transformer architecture is invariant to such positions as long as you avoid the positional embedding.
I have a multi-dimensional, hyper-spectral image (channels, width, height = 15, 2500, 2500). I want to compress its 15 channel dimensions into 5 channels.So, the output would be (channels, width, height = 5, 2500, 2500). One simple way to do is to apply PCA. However, performance is not so good. Thus, I want to use Variational AutoEncoder(VAE).
When I saw the available solution in Tensorflow or keras library, it shows an example of clustering the whole images using Convolutional Variational AutoEncoder(CVAE).
https://www.tensorflow.org/tutorials/generative/cvae
https://keras.io/examples/generative/vae/
However, I have a single image. What is the best practice to implement CVAE? Is it by generating sample images by moving window approach?
One way of doing it would be to have a CVAE that takes as input (and output) values of all the spectral features for each of the spatial coordinates (the stacks circled in red in the picture). So, in the case of your image, you would have 2500*2500 = 6250000 input data samples, which are all vectors of length 15. And then the dimension of the middle layer would be a vector of length 5. And, instead of 2D convolutions that are normally used along the spatial domain of images, in this case it would make sense to use 1D convolution over the spectral domain (since the values of neighbouring wavelengths are also correlated). But I think using only fully-connected layers would also make sense.
As a disclaimer, I haven’t seen CVAEs used in this way before, but like this, you would also get many data samples, which is needed in order for the learning generalise well.
Another option would be indeed what you suggested -- to just generate the samples (patches) using a moving window (maybe with a stride that is the half size of the patch). Even though you wouldn't necessarily get enough data samples for the CVAE to generalise really well on all HSI images, I guess it doesn't matter (if it overfits), since you want to use it on that same image.
Imagine I have hundreds of rectangular patterns that look like the following:
_yx_0zzyxx
_0__yz_0y_
x0_0x000yx
_y__x000zx
zyyzx_z_0y
Say the only variables for the different patterns are dimension (width by height in characters) and values at a given cell within the rectangle with possible characters _ y x z 0. So another pattern might look like this:
yx0x_x
xz_x0_
_yy0x_
zyy0__
and another like this:
xx0z00yy_z0x000
zzx_0000_xzzyxx
_yxy0y__yx0yy_z
_xz0z__0_y_xz0z
y__x0_0_y__x000
xz_x0_z0z__0_x0
These simplified examples were randomly generated, but imagine there is a deeper structure and relation between dimensions and layout of characters.
I want to train on this dataset in an unsupervised fashion (no labels) in order to generate similar output. Assuming I have created my dataset appropriately with tf.data.Dataset and categorical identity columns:
what is a good general purpose model for unsupervised training (no labels)?
is there a Tensorflow premade estimator that would represent such a model well enough?
once I've trained the model, what is a general approach to using it for generation of patterns based on what it has learned? I have in mind Google Magenta, which can be used to train on a dataset of musical melodies in order to generate similar ones from a kind of seed/primer melody
I'm not looking for a full implementation (that's the fun part!), just some suggested tutorials and next steps to follow. Thanks!
I am training an object detector for my own data using Tensorflow Object Detection API. I am following the (great) tutorial by Dat Tran https://towardsdatascience.com/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9. I am using the provided ssd_mobilenet_v1_coco-model pre-trained model checkpoint as the starting point for the training. I have only one object class.
I exported the trained model, ran it on the evaluation data and looked at the resulted bounding boxes. The trained model worked nicely; I would say that if there was 20 objects, typically there were 13 objects with spot on predicted bounding boxes ("true positives"); 7 where the objects were not detected ("false negatives"); 2 cases where problems occur were two or more objects are close to each other: the bounding boxes get drawn between the objects in some of these cases ("false positives"<-of course, calling these "false positives" etc. is inaccurate, but this is just for me to understand the concept of precision here). There are almost no other "false positives". This seems much better result than what I was hoping to get, and while this kind of visual inspection does not give the actual mAP (which is calculated based on overlap of the predicted and tagged bounding boxes?), I would roughly estimate the mAP as something like 13/(13+2) >80%.
However, when I run the evaluation (eval.py) (on two different evaluation sets), I get the following mAP graph (0.7 smoothed):
mAP during training
This would indicate a huge variation in mAP, and level of about 0.3 at the end of the training, which is way worse than what I would assume based on how well the boundary boxes are drawn when I use the exported output_inference_graph.pb on the evaluation set.
Here is the total loss graph for the training:
total loss during training
My training data consist of 200 images with about 20 labeled objects each (I labeled them using the labelImg app); the images are extracted from a video and the objects are small and kind of blurry. The original image size is 1200x900, so I reduced it to 600x450 for the training data. Evaluation data (which I used both as the evaluation data set for eval.pyand to visually check what the predictions look like) is similar, consists of 50 images with 20 object each, but is still in the original size (the training data is extracted from the first 30 min of the video and evaluation data from the last 30 min).
Question 1: Why is the mAP so low in evaluation when the model appears to work so well? Is it normal for the mAP graph fluctuate so much? I did not touch the default values for how many images the tensorboard uses to draw the graph (I read this question: Tensorflow object detection api validation data size and have some vague idea that there is some default value that can be changed?)
Question 2: Can this be related to different size of the training data and the evaluation data (1200x700 vs 600x450)? If so, should I resize the evaluation data, too? (I did not want to do this as my application uses the original image size, and I want to evaluate how well the model does on that data).
Question 3: Is it a problem to form the training and evaluation data from images where there are multiple tagged objects per image (i.e. surely the evaluation routine compares all the predicted bounding boxes in one image to all the tagged bounding boxes in one image, and not all the predicted boxes in one image to one tagged box which would preduce many "false false positives"?)
(Question 4: it seems to me the model training could have been stopped after around 10000 timesteps were the mAP kind of leveled out, is it now overtrained? it's kind of hard to tell when it fluctuates so much.)
I am a newbie with object detection so I very much appreciate any insight anyone can offer! :)
Question 1: This is the tough one... First, I think you don't understand correctly what mAP is, since your rough calculation is false. Here is, briefly, how it is computed:
For each class of object, using the overlap between the real objects and the detected ones, the detections are tagged as "True positive" or "False positive"; all the real objects with no "True positive" associated to them are labelled "False Negative".
Then, iterate through all your detections (on all images of the dataset) in decreasing order of confidence. Compute the accuracy (TP/(TP+FP)) and recall (TP/(TP+FN)), only counting the detections that you've already seen ( with confidence bigger than the current one) for TP and FP. This gives you a point (acc, recc), that you can put on a precision-recall graph.
Once you've added all possible points to your graph, you compute the area under the curve: this is the Average Precision for this category
if you have multiple categories, the mAP is the standard mean of all APs.
Applying that to your case: in the best case your true positive are the detections with the best confidence. In that case your acc/rec curve will look like a rectangle: you'd have 100% accuracy up to (13/20) recall, and then points with 13/20 recall and <100% accuracy; this gives you mAP=AP(category 1)=13/20=0.65. And this is the best case, you can expect less in practice due to false positives which higher confidence.
Other reasons why yours could be lower:
maybe among the bounding boxes that appear to be good, some are still rejected in the calculations because the overlap between the detection and the real object is not quite big enough. The criterion is that Intersection over Union (IoU) of the two bounding boxes (real one and detection) should be over 0.5. While it seems like a gentle threshold, it's not really; you should probably try and write a script to display the detected bounding boxes with a different color depending on whether they're accepted or not (if not, you'll get both a FP and a FN).
maybe you're only visualizing the first 10 images of the evaluation. If so, change that, for 2 reasons: 1. maybe you're just very lucky on these images, and they're not representative of what follows, just by luck. 2. Actually, more than luck, if these images are the first from the evaluation set, they come right after the end of the training set in your video, so they are probably quite similar to some images in the training set, so they are easier to predict, so they're not representative of your evaluation set.
Question 2: if you have not changed that part in the config file mobilenet_v1_coco-model, all your images (both for training and testing) are rescaled to 300x300 pixels at the start of the network, so your preprocessings don't matter.
Question 3: no it's not a problem at all, all these algorithms were designed to detect multiple objects in images.
Question 4: Given the fluctuations, I'd actually keep training it until you can see improvement or clear overtraining. 10k steps is actually quite small, maybe it's enough because your task is relatively easy, maybe it's not enough and you need to wait ten times that to have significant improvement...
I download the following graph-cut code:
https://github.com/shaibagon/GCMex
I compiled the mex files, and ran it for pre-defined image in the code (which is rgb image)
I wanna optimize the image segmentation results,
I have probability map of the image, which its dimension is (width,height, 5). Five probability distribution over the image dimension are stacked together. each relates to one the classes.
My problem is which parts of code should according to the probability image.
I want to define Data and Smoothing terms based on my application.
My question is:
1) Has someone refined the code according to the defining different energy function (I wanna change Unary and pair-wise formulation).
2) I have a stack of 3D images. I wanna define 6-neighborhood system, 4 neighbors in current slice and the other two from two adjacent slices. In which function and part of code can I do the refinements?
Thanks