Comments (9)
I have never tested this with outputting more than one frame at a time. The original paper added some extra tricks to make that work well. But the easiest way to tweak this to do what you want is in constants.py
set HIST_LEN = 10
and in SCALE_FMS_G
, set the last element of each array (currently all 3s) to be 9 (3 channels * 3 output frames). You will have to write something to parse the output, since it will be all 3 images stacked on top of one another.
This may also break some of the training loop that has to do with visualizing the images, since those functions are expecting 3-channel inputs.
Let me know how this works for you! And be sure to use TensorFlow 0.12 (doesn't work on the latest versions yet)
from adversarial_video_generation.
Thank you for your kindly reply.
The original paper gave the models of 8 input frames and 8 output frames. Can I just modify the SCALE_CONV_FMS, SCALE_KERNEL_SIZES and SCALE_FC_LAYER_SIZES. set HIST_LEN=8 to get
the 8 prediction frames?
Best wishes!
from adversarial_video_generation.
Yes, after re-reading that section of the paper, if you tweak those hyperparameters it should work.
Please let me know how it turns out!
from adversarial_video_generation.
I don't understand why you add a column to SCALE_CONV_FMS_D, SCALE_FMS_G, SCALE_FC_LAYER_SIZES_D, instead of just using the models of 4 inputs and 1 output provided by
the original paper? when I tweak those hyperparameters for 8 inputs and 8 outputs, need I add it too?
from adversarial_video_generation.
I don't understand your question. Could you point to the piece of code you are confused about, and give an example of what you think it should be?
from adversarial_video_generation.
In your code,
SCALE_FMS_G = [[3 * HIST_LEN, 128, 256, 128, 3],
[3 * (HIST_LEN + 1), 128, 256, 128, 3],
[3 * (HIST_LEN + 1), 128, 256, 512, 256, 128, 3],
[3 * (HIST_LEN + 1), 128, 256, 512, 256, 128, 3]]
There are not the first and the last columns in the original paper. why do you add them? Can you explain
it. Thank you
from adversarial_video_generation.
The first column is the depth of the input (3 channels * the number of input frames), and the last column is the depth of the output (3 channels * 1 output frame). I set it up this way so it would be easy to change the number of input or output frames
from adversarial_video_generation.
I have some data which is 883 instead of your training data 32323. I just revise the TRAIN_HEIGHT & TRAIN_WIDTH to 8. but when running to preds = tf.nn.conv2d(last_input, conv_ws[i], [1, 1, 1, 1], padding=c.PADDING_D). there is an error:ValueError: Negative dimension size caused by subtracting 3 from 1 for 'discriminator/scale_net_0/calculation/convolutions/Conv2D' (op: 'Conv2D') with input shapes: [?,1,1,3], [3,3,3,64].
what else should I revise? Thank u
from adversarial_video_generation.
I'm guessing this is because there are four scale networks that each downsample the image by 2x, so if your original images are 8 pixels wide, the image input to the smallest scale network will be 1 pixel, which could be too small to convolve over with 3x3 or 5x5 kernels
from adversarial_video_generation.
Related Issues (20)
- Confusion using the plug-and-play data HOT 5
- Regarding the normalization step HOT 4
- problem about exist model HOT 4
- Some problem about gdl_loss HOT 1
- Question about discriminator input HOT 3
- What do the output images represent? HOT 12
- Normalization of losses
- Why need the data processing step? HOT 3
- Error with np.random.choice HOT 4
- What is PSNR error exactly? HOT 3
- Can you share the code that generates the gif file? HOT 2
- TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64
- Alternative GDL loss implemetation
- Loss weighting HOT 1
- ValueError: Dimension 3 in both shapes must be equal HOT 1
- Updating Code to New Tensorflow version HOT 2
- GLARING bug with the process data pipeline.
- TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64 HOT 1
- ValueError: Dimensions must be equal, but are 1 and 3 for 'generator/train/Conv2D' (op: 'Conv2D') with input shapes: [?,4,4,1], [1,2,3,3].
- Tensorflow and packages are out of date
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from adversarial_video_generation.