refactor

app.py

@@ -1,15 +1,11 @@
-import json
-import os
 import random
 import time
 from functools import partial
-from pathlib import Path
 from typing import List
 
 import deepinv as dinv
 import gradio as gr
 import torch
-from PIL import Image
 from torchvision import transforms
 
 from factories import PhysicsWithGenerator, EvalModel, BaselineModel, EvalDataset, Metric
@@ -163,9 +159,9 @@ def get_dataset(dataset_name):
         physics_name = 'CT'
         baseline_name = 'DPIR_CT'
     else:
-        available_physics = ['MotionBlur_easy', 'MotionBlur_medium', 'MotionBlur_hard',
+        available_physics = ['MotionBlur_medium', 'MotionBlur_hard',
                              'GaussianBlur_easy', 'GaussianBlur_medium', 'GaussianBlur_hard']
-        physics_name = 'MotionBlur_easy'
+        physics_name = 'MotionBlur_hard'
         baseline_name = 'DPIR'
 
     dataset = get_dataset_on_DEVICE_STR(dataset_name)

factories.py

@@ -37,7 +37,7 @@ DEFAULT_MODEL_PARAMS = {
 
 class PhysicsWithGenerator(torch.nn.Module):
     """Interface between Physics, Generator and Gradio."""
-    all_physics = ["MotionBlur_easy", "MotionBlur_medium", "MotionBlur_hard",
+    all_physics = ["MotionBlur_medium", "MotionBlur_hard",
                    "GaussianBlur_easy", "GaussianBlur_medium", "GaussianBlur_hard",
                    "MRI", "CT"]
 
@@ -48,17 +48,7 @@ class PhysicsWithGenerator(torch.nn.Module):
         if self.name not in self.all_physics:
             raise ValueError(f"{self.name} is unavailable.")
 
-        if self.name == "MotionBlur_easy":
-            psf_size = 31
-            self.physics = dinv.physics.Blur(noise_model=dinv.physics.GaussianNoise(sigma=.01),
-                                             padding="valid", device=device_str)
-            self.physics_generator = MotionBlurGenerator((psf_size, psf_size), l=0.1, sigma=0.1, device=device_str)
-            self.generator = self.physics_generator + SigmaGenerator(sigma_min=0.01, sigma_max=0.01, device=device_str)
-            self.saved_params = {"updatable_params": {"sigma": 0.01},
-                                 "updatable_params_converter": {"sigma": float},
-                                 "fixed_params": {"noise_sigma_min": 0.01, "noise_sigma_max": 0.01,
-                                                  "psf_size": 31, "motion_gen_l": 0.1, "motion_gen_s": 0.1}}
-        elif self.name == "MotionBlur_medium":
+        if self.name == "MotionBlur_medium":
             psf_size = 31
             self.physics = dinv.physics.Blur(noise_model=dinv.physics.GaussianNoise(sigma=.05),
                                              padding="valid", device=device_str)
@@ -128,8 +118,7 @@ class PhysicsWithGenerator(torch.nn.Module):
         elif self.name == "CT":
             acceleration_factor = 10
             img_h = 512
-            angles = int(img_h / acceleration_factor)
-            # angles = torch.linspace(0, 180, steps=10)
+            angles = torch.linspace(0, 180, steps=int(img_h / acceleration_factor))
             self.physics = dinv.physics.Tomography(
                 img_width=img_h,
                 angles=angles,
@@ -188,7 +177,7 @@ class PhysicsWithGenerator(torch.nn.Module):
         self.physics.update(**kwargs)
 
     def forward(self, x: torch.Tensor, use_gen: bool) -> torch.Tensor:
-        if self.name in ["MotionBlur_easy", "MotionBlur_medium", "MotionBlur_hard", "GaussianBlur_easy", "GaussianBlur_medium", "GaussianBlur_hard"] and not hasattr(self.physics, "filter"):
+        if self.name in ["MotionBlur_medium", "MotionBlur_hard", "GaussianBlur_easy", "GaussianBlur_medium", "GaussianBlur_hard"] and not hasattr(self.physics, "filter"):
             use_gen = True
         elif self.name in ["MRI"] and not hasattr(self.physics, "mask"):
             use_gen = True