can not find sample image

Hi, i met a problem when i run sh scripts/maml/sample_mnist.sh. i can not find the sample image. i open the dir ( inr_minst/samples) but it was empty. however , when i run exp_ninist. it will generate image. could you give me some instructions?

best,
xinxin

[giulio98]

Hello, @cindyyyl !
Does the sampled image are correctly displayed on wandb?

Copy that, I saw it , but i find maybe the key problem is i did not run them sucessfully. I stuck in the evaluation part, i try to adjust the number of samples from 10001 to 10000( i think it was a bug ) ,and i am sure that the both dir has file end with xxx.npz. could you give me any instructions?

[giulio98]

Hello @cindyyyl,

Sorry for the late reply. To better assist you, I need that you describe better your issue could you please fill out the following details, please:

1. Steps to Reproduce:

   • Step 1:
   • Step 2:
   • Step 3:

2. Expected Behavior:

   • What you expected to happen after completing the steps above.

3. Actual Behavior:

   • What actually happened. Please include any error messages or screenshots if possible.

4. Additional Information:

   • Any other details or context you think might be helpful.

Best regards,

Giulio

Hi Giulio, Sorry for the late reply. the steps of what i did are : [image: image.png] [image: image.png] [image: image.png] [image: image.png] [image: image.png] the bug of fid.compute() i have already solved , it because this function need 3 chanels but the .npy file sampled in evaluation only 1 chanel. however, after i solved this problem. my fid is nan and fid clip was three times of yours exp. I think email communication maybe not a efficient way. do you have time to have a zoom meeting? Besides that, your work is really wonderful ! Thank you ! best, xinxin Giulio Corallo ***@***.***> 于2024年3月30日周六 11:42写道：

…

Hello, @cindyyyl <https://github.com/cindyyyl> ! Does the sampled image are correctly displayed on wandb? — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AY3WWQ44PHFKUTJX3DMR2ADY23FM3AVCNFSM6AAAAABE6MZ37KVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAMRYGE2DCMRTGI> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[giulio98]

Hello @cindyyyl,

It appears there's some confusion regarding the FID calculations for MNIST. The FID Clean and FID Clip scores cannot be computed with the current setup as the feature extractor networks require images with 3 channels. However, for MNIST, we've utilized a pretrained LeNet5, using its penultimate layer to extract features for the standard FID computation.

You can verify in the configuration file that LeNet is specified as the feature extractor for MNIST at this link:

functional-diffusion-processes/conf/metrics/metrics_mnist.yaml

Line 8 in cb13fb0

model_name: "lenet"

.

Additionally, we have provided the pretrained LeNet5 model weights in the models/lenet5 for reproducibility.

Therefore, it is expected that you won’t be able to obtain the FID CLIP and FID Clean scores—it’s not a bug. Could you confirm if you were able to calculate the standard FID score? If so, I'll initiate a pull request to clarify that FID CLIP and FID Clean scores should not be computed when dealing with single-channel images, to avoid further confusion.

Best regards,
Giulio

Hi Giulio， Thank you so much for you details instructions. It really helps me a lot ! however, i just want to the fid score and do not have much interest for FID clean and clip. For fid score caculation , i did not do any other operations(I do not change the channel of .npz for fid score caculation), just follow the instruction of github. however , the fid score is nan. Thank you again ! best, xinxin [image: image.png] Giulio Corallo ***@***.***> 于2024年5月2日周四 05:57写道：

…

Hello @cindyyyl <https://github.com/cindyyyl>, It appears there's some confusion regarding the FID calculations for MNIST. The FID Clean and FID Clip scores cannot be computed with the current setup as the feature extractor networks require images with 3 channels. However, for MNIST, we've utilized a pretrained LeNet5, using its penultimate layer to extract features for the standard FID computation. You can verify in the configuration file that LeNet is specified as the feature extractor for MNIST at this link: https://github.com/giulio98/functional-diffusion-processes/blob/cb13fb08b8f1a5449d627c6c9dd2b964e52852dd/conf/metrics/metrics_mnist.yaml#L8 . Additionally, we have provided the pretrained LeNet5 model weights in the models/lenet5 for reproducibility. Therefore, it is expected that you won’t be able to obtain the FID CLIP and FID Clean scores—it’s not a bug. Could you confirm if you were able to calculate the standard FID score? If so, I'll initiate a pull request to clarify that FID CLIP and FID Clean scores should not be computed when dealing with single-channel images, to avoid further confusion. Best regards, Giulio — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AY3WWQ5X6QLCOJIHYCDRU3DZAIEYVAVCNFSM6AAAAABE6MZ37KVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJQGA3DMMJTHA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[giulio98]

Hi,

Can you send here a screenshot of a batch for the sampled image for mnist?

HI Giulio, how about this, i have already zip projects (include the images i sampled in evaluation process). i pull it to your repo? best, xinxin Giulio Corallo ***@***.***> 于2024年4月26日周五 19:49写道：

…

Hello @cindyyyl <https://github.com/cindyyyl>, Sorry for the late reply. To better assist you, I need that you describe better your issue could you please fill out the following details, please: 1. *Steps to Reproduce:* - Step 1: - Step 2: - Step 3: 2. *Expected Behavior:* - What you expected to happen after completing the steps above. 3. *Actual Behavior:* - What actually happened. Please include any error messages or screenshots if possible. 4. *Additional Information:* - Any other details or context you think might be helpful. Best regards, Giulio — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AY3WWQ2ON2RXDPX2PWQ7YF3Y7LRZBAVCNFSM6AAAAABE6MZ37KVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOBQGI2DCNJQGQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[image: image.png][image: image.png] [image: image.png] Giulio Corallo ***@***.***> 于2024年5月3日周五 02:38写道：

…

Hi, Can you send here a screenshot of a batch for the sampled image for mnist? — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AY3WWQ5LMYZBJNZ6AZLXJGTZAMWFBAVCNFSM6AAAAABE6MZ37KVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJSGM4TGOBRHA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[giulio98]

Hey sorry I can't see your screenshot. I just see [image.png] can you try again?

Hi Giulio, Could we talk about it recently or what other information you want to know ? since the DDL of my master thesis is coming soon, r my exp did not have any result as so far \cry\cry. best, xinxin

…

On Sat, May 4, 2024 at 10:45 PM cv zx ***@***.***> wrote: On Sat, May 4, 2024 at 10:04 PM Giulio Corallo ***@***.***> wrote: > Hey sorry I can't see your screenshot. I just see [image.png] can you try > again? > > — > Reply to this email directly, view it on GitHub > <#6 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AY3WWQ5RTEI6DE7N7ZR533TZAWHTNAVCNFSM6AAAAABE6MZ37KVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJUGU2TEMBRGI> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >

[giulio98]

Hello, I run the script and i was able to get the FID score for mnist
This is my full log:

(fdp) corallo@atlas1:~/PycharmProjects/functional-diffusion-processes$ sh scripts/maml/eval_mnist.sh
2024-05-05 15:39:17.027317: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.1 SSE4.2 AVX AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
[2024-05-05 15:39:19,697][HYDRA] Launching 1 jobs locally
[2024-05-05 15:39:19,697][HYDRA]        #0 : +experiments_maml=eval_mnist
[2024-05-05 15:39:19,880][__main__][INFO] - Instantiating <functional_diffusion_processes.datasets.mnist_dataset.MNISTDataset>
/home/corallo/miniconda3/envs/fdp/lib/python3.10/site-packages/pydub/utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work
  warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)
[2024-05-05 15:39:20,082][absl][WARNING] - options.experimental_threading is deprecated. Use options.threading instead.
[2024-05-05 15:39:20,082][absl][WARNING] - options.experimental_threading is deprecated. Use options.threading instead.
[2024-05-05 15:39:20,087][absl][INFO] - Load dataset info from /home/corallo/PycharmProjects/functional-diffusion-processes/data/tensorflow_datasets/mnist/3.0.1
[2024-05-05 15:39:20,089][__main__][INFO] - Instantiating <functional_diffusion_processes.datasets.mnist_dataset.MNISTDataset>
[2024-05-05 15:39:20,092][absl][WARNING] - options.experimental_threading is deprecated. Use options.threading instead.
[2024-05-05 15:39:20,092][absl][WARNING] - options.experimental_threading is deprecated. Use options.threading instead.
[2024-05-05 15:39:20,092][absl][INFO] - Load dataset info from /home/corallo/PycharmProjects/functional-diffusion-processes/data/tensorflow_datasets/mnist/3.0.1
[2024-05-05 15:39:20,093][__main__][INFO] - Instantiating <functional_diffusion_processes.models.mlp_modulation.MLPModulationLR>
[2024-05-05 15:39:20,127][__main__][INFO] - Instantiating <functional_diffusion_processes.sdetools.heat_subvp_sde.HeatSubVPSDE>
[2024-05-05 15:39:20,209][absl][INFO] - Unable to initialize backend 'tpu_driver': NOT_FOUND: Unable to find driver in registry given worker: 
[2024-05-05 15:39:20,776][absl][INFO] - Unable to initialize backend 'rocm': NOT_FOUND: Could not find registered platform with name: "rocm". Available platform names are: Interpreter Host CUDA
[2024-05-05 15:39:20,777][absl][INFO] - Unable to initialize backend 'tpu': module 'jaxlib.xla_extension' has no attribute 'get_tpu_client'
[2024-05-05 15:39:20,777][absl][INFO] - Unable to initialize backend 'plugin': xla_extension has no attributes named get_plugin_device_client. Compile TensorFlow with //tensorflow/compiler/xla/python:enable_plugin_device set to true (defaults to false) to enable this.
[2024-05-05 15:39:21,560][__main__][INFO] - Instantiating <functional_diffusion_processes.samplers.correctors.langevin_corrector.LangevinCorrector>
[2024-05-05 15:39:21,564][__main__][INFO] - Instantiating <functional_diffusion_processes.samplers.predictors.euler_predictor.EulerMaruyamaPredictor>
[2024-05-05 15:39:21,568][__main__][INFO] - Instantiating <functional_diffusion_processes.samplers.pc_sampler.PCSampler>
[2024-05-05 15:39:21,571][__main__][INFO] - Instantiating <functional_diffusion_processes.losses.mse_loss.MSELoss>
[2024-05-05 15:39:21,573][__main__][INFO] - Instantiating <functional_diffusion_processes.trainers.trainer.Trainer>
[2024-05-05 15:39:21,591][absl][WARNING] - GlobalAsyncCheckpointManager is not imported correctly. Checkpointing of GlobalDeviceArrays will not be available.To use the feature, install tensorstore.
WARNING:tensorflow:From /home/corallo/miniconda3/envs/fdp/lib/python3.10/site-packages/tensorflow_gan/python/estimator/tpu_gan_estimator.py:42: The name tf.estimator.tpu.TPUEstimator is deprecated. Please use tf.compat.v1.estimator.tpu.TPUEstimator instead.

[2024-05-05 15:39:23,457][tensorflow][WARNING] - From /home/corallo/miniconda3/envs/fdp/lib/python3.10/site-packages/tensorflow_gan/python/estimator/tpu_gan_estimator.py:42: The name tf.estimator.tpu.TPUEstimator is deprecated. Please use tf.compat.v1.estimator.tpu.TPUEstimator instead.

[2024-05-05 15:39:23,465][__main__][INFO] - Instantiating <functional_diffusion_processes.metrics.fid_metric.FIDMetric>
[2024-05-05 15:39:23,604][functional_diffusion_processes.metrics.feature_extractor][INFO] - Extracting features from dataset...
[2024-05-05 15:39:23,605][absl][INFO] - Reusing dataset mnist (/home/corallo/PycharmProjects/functional-diffusion-processes/data/tensorflow_datasets/mnist/3.0.1)
[2024-05-05 15:39:23,640][absl][INFO] - Constructing tf.data.Dataset mnist for split test, from /home/corallo/PycharmProjects/functional-diffusion-processes/data/tensorflow_datasets/mnist/3.0.1
WARNING:tensorflow:AutoGraph could not transform <bound method PercentStyle._format of <logging.PercentStyle object at 0x7fb89752cb80>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: 'NoneType' object has no attribute '_fields'
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
[2024-05-05 15:39:25,504][tensorflow][WARNING] - AutoGraph could not transform <bound method PercentStyle._format of <logging.PercentStyle object at 0x7fb89752cb80>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: 'NoneType' object has no attribute '_fields'
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
[2024-05-05 15:39:24,513][functional_diffusion_processes.datasets.mnist_dataset][INFO] - Converting image to range [0,1]...
[2024-05-05 15:39:25,637][functional_diffusion_processes.datasets.mnist_dataset][INFO] - Resizing image to size 32...
[2024-05-05 15:39:25,661][functional_diffusion_processes.datasets.image_dataset][INFO] - Preprocessing images for split test...
[2024-05-05 15:39:25,682][functional_diffusion_processes.datasets.image_dataset][INFO] - Image reshaped to shape (1024, 1)...
/home/corallo/miniconda3/envs/fdp/lib/python3.10/site-packages/jax/_src/lib/xla_bridge.py:544: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
  warnings.warn(
[2024-05-05 15:39:25,912][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 0
/home/corallo/miniconda3/envs/fdp/lib/python3.10/site-packages/tensorflow/python/util/nest.py:917: UserWarning: `tf.layers.flatten` is deprecated and will be removed in a future version. Please use `tf.keras.layers.Flatten` instead.
  structure[0], [func(*x) for x in entries],
/home/corallo/miniconda3/envs/fdp/lib/python3.10/site-packages/keras/legacy_tf_layers/base.py:627: UserWarning: `layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically.
  self.updates, tf.compat.v1.GraphKeys.UPDATE_OPS
[2024-05-05 15:39:27,005][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 1
[2024-05-05 15:39:27,542][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 2
[2024-05-05 15:39:28,074][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 3
[2024-05-05 15:39:28,655][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 4
[2024-05-05 15:39:29,643][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 5
[2024-05-05 15:39:30,365][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 6
[2024-05-05 15:39:30,861][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 7
[2024-05-05 15:39:31,510][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 8
[2024-05-05 15:39:32,186][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 9
[2024-05-05 15:39:32,710][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 10
[2024-05-05 15:39:33,367][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 11
[2024-05-05 15:39:34,191][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 12
[2024-05-05 15:39:34,736][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 13
[2024-05-05 15:39:35,238][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 14
[2024-05-05 15:39:35,738][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 15
[2024-05-05 15:39:36,249][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 16
[2024-05-05 15:39:36,761][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 17
[2024-05-05 15:39:37,254][functional_diffusion_processes.metrics.feature_extractor][INFO] - Making FID stats -- step 18
[2024-05-05 15:39:37,758][functional_diffusion_processes.metrics.fid_metric][INFO] - Saving real dataset stats to: /home/corallo/PycharmProjects/functional-diffusion-processes/data/stats/mnist_test_stats.npz
[2024-05-05 15:39:37,980][__main__][INFO] - Starting testing!
wandb: Currently logged in as: giulio-corallo (eurecom-ds). Use `wandb login --relogin` to force relogin
wandb: wandb version 0.16.6 is available!  To upgrade, please run:
wandb:  $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.14.0
wandb: Run data is saved locally in /home/corallo/PycharmProjects/functional-diffusion-processes/wandb/run-20240505_153938-lk5wmrth
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run inr_mnist
wandb: ⭐️ View project at https://wandb.ai/eurecom-ds/fpd
wandb: 🚀 View run at https://wandb.ai/eurecom-ds/fpd/runs/lk5wmrth
[2024-05-05 15:39:48,607][functional_diffusion_processes.trainers.trainer][INFO] - Total number of parameters: 0.12M
[2024-05-05 15:39:48,904][functional_diffusion_processes.trainers.trainer][WARNING] - Resuming training from the latest checkpoint.
[2024-05-05 15:39:48,905][absl][INFO] - Restoring checkpoint from /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/checkpoints/checkpoint_27
/home/corallo/miniconda3/envs/fdp/lib/python3.10/site-packages/jax/_src/lib/xla_bridge.py:544: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
  warnings.warn(
[2024-05-05 15:39:48,989][absl][INFO] - Found no checkpoint files in /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist with prefix meta_0_
[2024-05-05 15:39:48,989][functional_diffusion_processes.trainers.trainer][INFO] - Starting sampling loop at step 0.
  0%|                                                                                                                                                                                 | 0/32 [00:00<?, ?it/s][2024-05-05 15:39:48,990][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 0
[2024-05-05 15:41:24,948][absl][INFO] - Saving checkpoint at step: 0
[2024-05-05 15:41:24,952][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_0
  3%|█████▎                                                                                                                                                                   | 1/32 [01:35<49:34, 95.96s/it][2024-05-05 15:41:24,953][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 1
[2024-05-05 15:41:43,396][absl][INFO] - Saving checkpoint at step: 1
[2024-05-05 15:41:43,397][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_1
[2024-05-05 15:41:43,397][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_0
  6%|██████████▌                                                                                                                                                              | 2/32 [01:54<25:10, 50.36s/it][2024-05-05 15:41:43,397][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 2
[2024-05-05 15:42:01,615][absl][INFO] - Saving checkpoint at step: 2
[2024-05-05 15:42:01,618][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_2
[2024-05-05 15:42:01,619][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_1
  9%|███████████████▊                                                                                                                                                         | 3/32 [02:12<17:14, 35.69s/it][2024-05-05 15:42:01,619][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 3
[2024-05-05 15:42:19,896][absl][INFO] - Saving checkpoint at step: 3
[2024-05-05 15:42:19,897][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_3
[2024-05-05 15:42:19,897][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_2
 12%|█████████████████████▏                                                                                                                                                   | 4/32 [02:30<13:26, 28.81s/it][2024-05-05 15:42:19,898][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 4
[2024-05-05 15:42:38,094][absl][INFO] - Saving checkpoint at step: 4
[2024-05-05 15:42:38,096][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_4
[2024-05-05 15:42:38,097][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_3
 16%|██████████████████████████▍                                                                                                                                              | 5/32 [02:49<11:14, 24.99s/it][2024-05-05 15:42:38,097][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 5
[2024-05-05 15:42:56,403][absl][INFO] - Saving checkpoint at step: 5
[2024-05-05 15:42:56,404][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_5
[2024-05-05 15:42:56,404][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_4
 19%|███████████████████████████████▋                                                                                                                                         | 6/32 [03:07<09:50, 22.72s/it][2024-05-05 15:42:56,405][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 6
[2024-05-05 15:43:14,647][absl][INFO] - Saving checkpoint at step: 6
[2024-05-05 15:43:14,648][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_6
[2024-05-05 15:43:14,648][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_5
 22%|████████████████████████████████████▉                                                                                                                                    | 7/32 [03:25<08:51, 21.25s/it][2024-05-05 15:43:14,651][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 7
[2024-05-05 15:43:32,949][absl][INFO] - Saving checkpoint at step: 7
[2024-05-05 15:43:32,956][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_7
[2024-05-05 15:43:32,956][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_6
 25%|██████████████████████████████████████████▎                                                                                                                              | 8/32 [03:43<08:07, 20.32s/it][2024-05-05 15:43:32,957][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 8
[2024-05-05 15:43:51,240][absl][INFO] - Saving checkpoint at step: 8
[2024-05-05 15:43:51,242][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_8
[2024-05-05 15:43:51,244][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_7
 28%|███████████████████████████████████████████████▌                                                                                                                         | 9/32 [04:02<07:32, 19.68s/it][2024-05-05 15:43:51,244][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 9
[2024-05-05 15:44:09,502][absl][INFO] - Saving checkpoint at step: 9
[2024-05-05 15:44:09,505][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_9
[2024-05-05 15:44:09,506][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_8
 31%|████████████████████████████████████████████████████▌                                                                                                                   | 10/32 [04:20<07:03, 19.24s/it][2024-05-05 15:44:09,507][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 10
[2024-05-05 15:44:27,768][absl][INFO] - Saving checkpoint at step: 10
[2024-05-05 15:44:27,776][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_10
[2024-05-05 15:44:27,776][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_9
 34%|█████████████████████████████████████████████████████████▊                                                                                                              | 11/32 [04:38<06:37, 18.95s/it][2024-05-05 15:44:27,777][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 11
[2024-05-05 15:44:45,992][absl][INFO] - Saving checkpoint at step: 11
[2024-05-05 15:44:46,002][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_11
[2024-05-05 15:44:46,004][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_10
 38%|███████████████████████████████████████████████████████████████                                                                                                         | 12/32 [04:57<06:14, 18.73s/it][2024-05-05 15:44:46,005][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 12
[2024-05-05 15:45:04,337][absl][INFO] - Saving checkpoint at step: 12
[2024-05-05 15:45:04,339][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_12
[2024-05-05 15:45:04,340][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_11
 41%|████████████████████████████████████████████████████████████████████▎                                                                                                   | 13/32 [05:15<05:53, 18.61s/it][2024-05-05 15:45:04,341][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 13
[2024-05-05 15:45:22,587][absl][INFO] - Saving checkpoint at step: 13
[2024-05-05 15:45:22,591][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_13
[2024-05-05 15:45:22,594][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_12
 44%|█████████████████████████████████████████████████████████████████████████▌                                                                                              | 14/32 [05:33<05:33, 18.50s/it][2024-05-05 15:45:22,594][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 14
[2024-05-05 15:45:40,872][absl][INFO] - Saving checkpoint at step: 14
[2024-05-05 15:45:40,880][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_14
[2024-05-05 15:45:40,881][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_13
 47%|██████████████████████████████████████████████████████████████████████████████▊                                                                                         | 15/32 [05:51<05:13, 18.44s/it][2024-05-05 15:45:40,881][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 15
[2024-05-05 15:45:59,246][absl][INFO] - Saving checkpoint at step: 15
[2024-05-05 15:45:59,251][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_15
[2024-05-05 15:45:59,252][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_14
 50%|████████████████████████████████████████████████████████████████████████████████████                                                                                    | 16/32 [06:10<04:54, 18.42s/it][2024-05-05 15:45:59,252][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 16
[2024-05-05 15:46:17,534][absl][INFO] - Saving checkpoint at step: 16
[2024-05-05 15:46:17,538][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_16
[2024-05-05 15:46:17,538][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_15
 53%|█████████████████████████████████████████████████████████████████████████████████████████▎                                                                              | 17/32 [06:28<04:35, 18.38s/it][2024-05-05 15:46:17,539][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 17
[2024-05-05 15:46:35,893][absl][INFO] - Saving checkpoint at step: 17
[2024-05-05 15:46:35,899][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_17
[2024-05-05 15:46:35,900][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_16
 56%|██████████████████████████████████████████████████████████████████████████████████████████████▌                                                                         | 18/32 [06:46<04:17, 18.37s/it][2024-05-05 15:46:35,900][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 18
[2024-05-05 15:46:54,148][absl][INFO] - Saving checkpoint at step: 18
[2024-05-05 15:46:54,150][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_18
[2024-05-05 15:46:54,150][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_17
 59%|███████████████████████████████████████████████████████████████████████████████████████████████████▊                                                                    | 19/32 [07:05<03:58, 18.34s/it][2024-05-05 15:46:54,151][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 19
[2024-05-05 15:47:12,467][absl][INFO] - Saving checkpoint at step: 19
[2024-05-05 15:47:12,468][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_19
[2024-05-05 15:47:12,469][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_18
 62%|█████████████████████████████████████████████████████████████████████████████████████████████████████████                                                               | 20/32 [07:23<03:39, 18.33s/it][2024-05-05 15:47:12,469][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 20
[2024-05-05 15:47:30,717][absl][INFO] - Saving checkpoint at step: 20
[2024-05-05 15:47:30,718][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_20
[2024-05-05 15:47:30,719][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_19
 66%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████▎                                                         | 21/32 [07:41<03:21, 18.31s/it][2024-05-05 15:47:30,719][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 21
[2024-05-05 15:47:49,020][absl][INFO] - Saving checkpoint at step: 21
[2024-05-05 15:47:49,026][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_21
[2024-05-05 15:47:49,026][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_20
 69%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌                                                    | 22/32 [08:00<03:03, 18.31s/it][2024-05-05 15:47:49,027][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 22
[2024-05-05 15:48:07,384][absl][INFO] - Saving checkpoint at step: 22
[2024-05-05 15:48:07,386][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_22
[2024-05-05 15:48:07,386][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_21
 72%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                                               | 23/32 [08:18<02:44, 18.32s/it][2024-05-05 15:48:07,387][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 23
[2024-05-05 15:48:25,666][absl][INFO] - Saving checkpoint at step: 23
[2024-05-05 15:48:25,671][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_23
[2024-05-05 15:48:25,672][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_22
 75%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████                                          | 24/32 [08:36<02:26, 18.31s/it][2024-05-05 15:48:25,672][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 24
[2024-05-05 15:48:43,856][absl][INFO] - Saving checkpoint at step: 24
[2024-05-05 15:48:43,861][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_24
[2024-05-05 15:48:43,862][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_23
 78%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎                                    | 25/32 [08:54<02:07, 18.28s/it][2024-05-05 15:48:43,862][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 25
[2024-05-05 15:49:02,126][absl][INFO] - Saving checkpoint at step: 25
[2024-05-05 15:49:02,128][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_25
[2024-05-05 15:49:02,129][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_24
 81%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌                               | 26/32 [09:13<01:49, 18.27s/it][2024-05-05 15:49:02,129][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 26
[2024-05-05 15:49:20,398][absl][INFO] - Saving checkpoint at step: 26
[2024-05-05 15:49:20,402][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_26
[2024-05-05 15:49:20,403][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_25
 84%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                          | 27/32 [09:31<01:31, 18.27s/it][2024-05-05 15:49:20,403][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 27
[2024-05-05 15:49:38,634][absl][INFO] - Saving checkpoint at step: 27
[2024-05-05 15:49:38,636][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_27
[2024-05-05 15:49:38,637][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_26
 88%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████                     | 28/32 [09:49<01:13, 18.26s/it][2024-05-05 15:49:38,637][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 28
[2024-05-05 15:49:56,883][absl][INFO] - Saving checkpoint at step: 28
[2024-05-05 15:49:56,885][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_28
[2024-05-05 15:49:56,885][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_27
 91%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎               | 29/32 [10:07<00:54, 18.26s/it][2024-05-05 15:49:56,886][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 29
[2024-05-05 15:50:15,084][absl][INFO] - Saving checkpoint at step: 29
[2024-05-05 15:50:15,089][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_29
[2024-05-05 15:50:15,089][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_28
 94%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌          | 30/32 [10:26<00:36, 18.24s/it][2024-05-05 15:50:15,090][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 30
[2024-05-05 15:50:33,486][absl][INFO] - Saving checkpoint at step: 30
[2024-05-05 15:50:33,487][absl][INFO] - Saved checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_30
[2024-05-05 15:50:33,488][absl][INFO] - Removing checkpoint at /home/corallo/PycharmProjects/functional-diffusion-processes/logs/inr_mnist/meta_0_29
 97%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊     | 31/32 [10:44<00:18, 18.29s/it][2024-05-05 15:50:33,488][functional_diffusion_processes.trainers.trainer][INFO] - sampling -- round: 31
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [11:02<00:00, 18.31s/it][2024-05-05 15:50:51,953][functional_diffusion_processes.trainers.trainer][INFO] - FID: 1.288000e+00
[2024-05-05 15:50:51,953][functional_diffusion_processes.trainers.trainer][INFO] - Inception score -1.000000e+00
wandb: Waiting for W&B process to finish... (success).
wandb: 
wandb: Run history:
wandb:             FID ▁
wandb: inception score ▁
wandb: 
wandb: Run summary:
wandb:             FID 1.288
wandb: inception score -1.0
wandb: 
wandb: 🚀 View run inr_mnist at: https://wandb.ai/eurecom-ds/fpd/runs/lk5wmrth
wandb: Synced 6 W&B file(s), 32 media file(s), 2 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20240505_153938-lk5wmrth/logs
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 32/32 [11:12<00:00, 21.01s/it]

Please do the following:
Synchronize your local repository with my changes
git pull

Carefully check your .env files
In my case is for example

export WANDB_API_KEY=<my secret wandb key>
export HOME=/home/corallo/PycharmProjects
export CUDA_HOME=/usr/local/cuda
export PROJECT_ROOT=/home/corallo/PycharmProjects/functional-diffusion-processes
export DATA_ROOT=${PROJECT_ROOT}/data
export LOGS_ROOT=${PROJECT_ROOT}/logs
export TFDS_DATA_DIR=${DATA_ROOT}/tensorflow_datasets
export PYTHONPATH=${PROJECT_ROOT}
export PYTHONUNBUFFERED=1
export HYDRA_FULL_ERROR=1
export WANDB_DISABLE_SERVICE=true
export CUDA_VISIBLE_DEVICES=2

please notice the following, HOME for me is /home/corallo/PycharmProjects because is the directory where is located the project functional-diffusion-processes in your case you have to check where is located yours -- we can't know in advance where is located.
Also PROJECT_ROOT for me is /home/corallo/PycharmProjects/functional-diffusion-processes which correspond to my HOME + functional-diffusion-processes

leave the others environment variables as is except you have to fill WANDB_API_KEY with yours and CUDA_VISIBLE_DEVICES with the ids (comma separated) of the GPUs you would like to use.

Let me know if after following this steps you are able to get the FID score.

Hi Giulio, I hope this email finds you well. I wanted to express my gratitude for your assistance – I've successfully run the FID score! Life can be quite challenging at times, but moments like these make it worthwhile. 😊 However, during the evaluation process in W&B, I noticed that the sampled images contain noise. Could you please advise on the configurations necessary to replicate the experimental results outlined in your paper? [image: image.png] Thank you once again for your help. Best regards, Xinxin Giulio Corallo ***@***.***> 于2024年4月26日周五 19:49写道：

…

Hello @cindyyyl <https://github.com/cindyyyl>, Sorry for the late reply. To better assist you, I need that you describe better your issue could you please fill out the following details, please: 1. *Steps to Reproduce:* - Step 1: - Step 2: - Step 3: 2. *Expected Behavior:* - What you expected to happen after completing the steps above. 3. *Actual Behavior:* - What actually happened. Please include any error messages or screenshots if possible. 4. *Additional Information:* - Any other details or context you think might be helpful. Best regards, Giulio — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AY3WWQ2ON2RXDPX2PWQ7YF3Y7LRZBAVCNFSM6AAAAABE6MZ37KVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOBQGI2DCNJQGQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[giulio98]

Hello,

I can't see the images you share with me.
This is what I see from your message:

Anyway this is a batch i get from the provided checkpoint