Network does not converge, bad captions #9
Comments
|
hi, I also have faced this problem. Let's work together to avoid this problem. My mail: [email protected]. Waiting for your answer |
|
It's been a while since I worked on this repo. I'll try to retrain it and reproduce this error sometime next week and see if something needs change. Meanwhile, @PavlosMelissinos and @MikhailovSergei if you were able to debug this, feel free to update and send a pull request. |
|
ok), will try too |
|
Hello, do u have the Flickr_30k.trainimages.txt and Flickr_30k.testimages.txt files. I can't find this files in anywhere=( In official web it's unable to download. I have image I need just this files |
|
Hello, |
|
Hi, I am glad to receive u comment. I have changed batch-size. I set it equal to 1500 instead 32 in capture_generator.py and train_model.py. after 43-45 epoch it can work a little better. Please give me know about u result and if u find some more better ways))) |
|
@MikhailovSergei @lopezlaura It actually depends on the dataset. Different datasets will ideally require us to tune hyperparameters to get optimal captions. It's not usual that we can reuse the hyperparameters. Things that you can try:
If it helps you improve your model, do post your results here for others to refer to. |
|
So what batch_size is better for Flickr 8k? |
|
I am facing the same issue while using Flickr8k and the captions are not making any sense. Particular words are getting repeated in every sentence. Somehow, it is working better on a subset of 100 images rather than the entire dataset. I have tried changing the batch size but it didn't help. Could you give any suggestions? |
|
After I trained the model , it gave me the result as follows: U can see the loss is high and the acc is low. Meanwhile, when I run the test_model, all of the output sentences are the same. I wanna know where to change learning rate and which optimization algorithm can be better? BTW, can you share ur weight file to me? My email address is [email protected] |
|
changing a batch size can improve accuracy . try it with 1024. |
|
I am a university student，can you share me model.save file，I want to see the effect. |
|
but if we take 1024 batch size it will be overfit |
|
@MikhailovSergei 1024batch need how much memory GPU |
|
can ur share me model.save file ?my networks doesn"t also converge thanks |
|
My networks doesn't converge, too. So maybe this is a bug. :( |
|
do u have else project for "image 2 caption" ?
if u have run window10 project，can u give me ?
2018-05-14 9:43 GMT+08:00 Shixiang Wan <[email protected]>:
… My networks doesn't converge, too. So maybe this is a bug. :(
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#9 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AeQNYp2WICrBieuXQn22ME3hw-E2FXnwks5tyOEugaJpZM4QK3bU>
.
|
|
@b10112157 Sorry, I have no other image caption projects, and no windows 10 image caption projects. But for this, tensorboard screenshot is the following:
|
|
Can u share ur best weight file?
從我的 iPhone 傳送
… Shixiang Wan ***@***.***> 於 2018年5月14日 上午9:58 寫道：
@b10112157 Sorry, I have no other image caption projects, and no windows 10 image caption projects. But for this, tensorboard screenshot is the following:
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or mute the thread.
|
|
@b10112157 Thanks for your kindly help. This my best weight and model file (epochs=50, batch_size=32): https://drive.google.com/open?id=1DlfecYfiPlViFCh1h9Op_6puaTAKwN0N |
|
how accuracy ? and best accuracy epoch where
2018-05-14 10:15 GMT+08:00 Shixiang Wan <[email protected]>:
… @b10112157 <https://github.com/b10112157> Thanks for your kindly help.
This my best weight and model file (epochs=50, batch_size=32):
https://drive.google.com/open?id=1DlfecYfiPlViFCh1h9Op_6puaTAKwN0N
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#9 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AeQNYgjXcMist2uw32-IvAlX4dILGMu9ks5tyOjDgaJpZM4QK3bU>
.
|
|
@b10112157 As shown in above tensorboard screenshot, the best loss is 5.502 (5th step) and the best accuracy is 0.3267 according to the best loss. |
|
@army3401 1024 batch need ~4.2GB GPU memory. This is my testing on single K80 GPU: |
|
My gpu is gtx1060 6g, run train batch 1024 have error,but batch 512 is ok
從我的 iPhone 傳送
… Shixiang Wan ***@***.***> 於 2018年5月14日 上午10:46 寫道：
@army3401 1024 batch need ~4.2GB GPU memory. This is my testing on single K80 GPU:
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or mute the thread.
|
|
@b10112157 Thanks. I am trying batch size 1024, and now the loss curve is apparent better than batch size 32. So maybe small batch size 32 results in the shock. |
|
can u share ur batch 1024 weight file ? becaus the batch set 1024 i had oom
，so my batch 512 epoch in 15x is the best ，but the acc only 0.6.
2018-05-14 13:32 GMT+08:00 Shixiang Wan <[email protected]>:
… @b10112157 <https://github.com/b10112157> Thanks. I am trying batch size
1024, and now the loss curve is apparent better than batch size 32. So
maybe small batch size 32 results in the shock.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#9 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AeQNYuEYSFGdT6YGs6IfK3JKTYmKHHpKks5tyRbagaJpZM4QK3bU>
.
|
|
@b10112157 This is 1024 batch size whole model file: Tensorboard screenshot: But I sample and test some pictures just now, the captions are bad. For example: |
|
it"s model okay? mymail :[email protected]
can u contact me?
2018-05-14 17:37 GMT+08:00 Shixiang Wan <[email protected]>:
… @b10112157 <https://github.com/b10112157> This is 1024 batch size whole
model file:
https://drive.google.com/open?id=1rK5OkeCAb_kJLKR6EKlVqd_HzlZrjrYn
Tensorboard screenshot:
[image: image]
<https://user-images.githubusercontent.com/9321757/39989790-77272774-579d-11e8-851c-fad78c723e92.png>
But I sample and test some pictures just now, the captions are bad. For
example:
[image: image]
<https://user-images.githubusercontent.com/9321757/39989726-4f06024c-579d-11e8-9183-fa8edd32e589.png>
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#9 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AeQNYpoU4XmYMh9-tMPH3Y8ZMeLDZpAlks5tyVBogaJpZM4QK3bU>
.
|
|
@ShixiangWan Hey,dear. |
|
It's not about the model, just replace 'unique = list(set(unique))' by 'unique = sorted(set(unique),key=unique.index)' in caption_generator.py, then results can make some sense. due to the batch size, my final loss is 2.23 and result like |
wow! It's great! I have the same problem,and i add the BN layer to stabilize the loss. but the best model's loss is 4.7 and the the acc is 0.37. Do you just adjust the batch size to 1024? |
How do you solve the problem? I try you solution but it does't work. The caption is excursive and has no sense . I don't know where is wrong ,please help me. |
how do you solve the problem? I try but it doesn't work.... |
|
I don't think setting batch_size to 32 will converge the training. I made the following settings:
|
Hello,
I've followed your instructions and started training the network. The loss reaches its minimum value after about 5 epochs and then it starts to diverge again.
After 50 epochs, the generated captions of the best epoch (5th or 6th) look like this:
Any idea what's wrong?
The text was updated successfully, but these errors were encountered: