CARE notebooks + remove os.chdir

HenriquesLab · Jul 31, 2023 · 8b0f1e0 · 8b0f1e0
1 parent a967f6d
commit 8b0f1e0
Show file tree

Hide file tree

Showing 7 changed files with 126 additions and 191 deletions.
diff --git a/Colab_notebooks/CARE_2D_ZeroCostDL4Mic.ipynb b/Colab_notebooks/CARE_2D_ZeroCostDL4Mic.ipynb
@@ -152,8 +152,8 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "3u2mXn3XsWzd",
-        "cellView": "form"
+        "cellView": "form",
+        "id": "3u2mXn3XsWzd"
       },
       "outputs": [],
       "source": [
@@ -203,8 +203,8 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "aGxvAcGT-rTq",
-        "cellView": "form"
+        "cellView": "form",
+        "id": "aGxvAcGT-rTq"
       },
       "outputs": [],
       "source": [
@@ -493,7 +493,7 @@
         "    pdf.set_font('Arial', size = 10, style = 'B')\n",
         "    pdf.cell(22, 5, txt= 'Model Path:', align = 'L', ln=0)\n",
         "    pdf.set_font('')\n",
-        "    pdf.multi_cell(170, 5, txt = model_path+'/'+model_name, align = 'L')\n",
+        "    pdf.multi_cell(170, 5, txt = full_model_path, align = 'L')\n",
         "    pdf.ln(1)\n",
         "    pdf.cell(60, 5, txt = 'Example Training pair', ln=1)\n",
         "    pdf.ln(1)\n",
@@ -516,7 +516,7 @@
         "    pdf.multi_cell(190, 5, txt=reminder, align='C')\n",
         "    pdf.ln(1)\n",
         "\n",
-        "    pdf.output(model_path+'/'+model_name+'/'+model_name+\"_training_report.pdf\")\n",
+        "    pdf.output(full_model_path+'/'+model_name+\"_training_report.pdf\")\n",
         "\n",
         "\n",
         "#Make a pdf summary of the QC results\n",
@@ -835,6 +835,7 @@
         "#@markdown ###Name of the model and path to model folder:\n",
         "model_name = \"\" #@param {type:\"string\"}\n",
         "model_path = \"\" #@param {type:\"string\"}\n",
+        "full_model_path = model_path+'/'+model_name\n",
         "\n",
         "# other parameters for training.\n",
         "#@markdown ###Training Parameters\n",
@@ -867,7 +868,7 @@
         "\n",
         "\n",
         "#here we check that no model with the same name already exist, if so print a warning\n",
-        "if os.path.exists(model_path+'/'+model_name):\n",
+        "if os.path.exists(full_model_path):\n",
         "  print(bcolors.WARNING +\"!! WARNING: \"+model_name+\" already exists and will be deleted in the following cell !!\")\n",
         "  print(bcolors.WARNING +\"To continue training \"+model_name+\", choose a new model_name here, and load \"+model_name+\" in section 3.3\"+W)\n",
         "  \n",
@@ -911,9 +912,7 @@
         "    patch_size = ((int(patch_size / 8)-1) * 8)\n",
         "    print (bcolors.WARNING + \" Your chosen patch_size is not divisible by 8; therefore the patch_size chosen is now:\",patch_size)\n",
         "\n",
-        "\n",
-        "os.chdir(Training_target)\n",
-        "y = imread(Training_target+\"/\"+random_choice)\n",
+        "y = imread(os.path.join(Training_target, random_choice))\n",
         "\n",
         "f=plt.figure(figsize=(16,8))\n",
         "plt.subplot(1,2,1)\n",
@@ -1129,8 +1128,7 @@
         "      \n",
         "\n",
         "  for filename in os.listdir(Training_source_augmented):\n",
-        "    os.chdir(Training_source_augmented)\n",
-        "    os.rename(filename, filename.replace('_original', ''))\n",
+        "    os.rename(os.path.join(Training_source_augmented,filename), os.path.join(Training_source_augmented,filename).replace('_original', ''))\n",
         "  \n",
         "  #Here we clean up the extra files\n",
         "  shutil.rmtree(Augmented_folder)\n",
@@ -1287,10 +1285,10 @@
         "\n",
         "# --------------------- Here we delete the model folder if it already exist ------------------------\n",
         "\n",
-        "if os.path.exists(model_path+'/'+model_name):\n",
+        "if os.path.exists(full_model_path):\n",
         "  print(bcolors.WARNING +\"!! WARNING: Model folder already exists and has been removed !!\"+W)\n",
-        "  shutil.rmtree(model_path+'/'+model_name)\n",
-        "\n",
+        "  shutil.rmtree(full_model_path)\n",
+        "os.makedirs(full_model_path, exist_ok=True)\n",
         "\n",
         "\n",
         "# --------------------- Here we load the augmented data or the raw data ------------------------\n",
@@ -1415,18 +1413,18 @@
         "print(\"Training, done.\")\n",
         "\n",
         "# copy the .npz to the model's folder\n",
-        "shutil.copyfile(model_path+'/rawdata.npz',model_path+'/'+model_name+'/rawdata.npz')\n",
+        "shutil.copyfile(model_path+'/rawdata.npz',full_model_path+'/rawdata.npz')\n",
         "\n",
         "# convert the history.history dict to a pandas DataFrame:     \n",
         "lossData = pd.DataFrame(history.history) \n",
         "\n",
-        "if os.path.exists(model_path+\"/\"+model_name+\"/Quality Control\"):\n",
-        "  shutil.rmtree(model_path+\"/\"+model_name+\"/Quality Control\")\n",
+        "if os.path.exists(full_model_path+\"/Quality Control\"):\n",
+        "  shutil.rmtree(full_model_path+\"/Quality Control\")\n",
         "\n",
-        "os.makedirs(model_path+\"/\"+model_name+\"/Quality Control\")\n",
+        "os.makedirs(full_model_path+\"/Quality Control\")\n",
         "\n",
         "# The training evaluation.csv is saved (overwrites the Files if needed). \n",
-        "lossDataCSVpath = model_path+'/'+model_name+'/Quality Control/training_evaluation.csv'\n",
+        "lossDataCSVpath = full_model_path+'/Quality Control/training_evaluation.csv'\n",
         "with open(lossDataCSVpath, 'w') as f:\n",
         "  writer = csv.writer(f)\n",
         "  writer.writerow(['loss','val_loss', 'learning rate'])\n",
@@ -1636,8 +1634,7 @@
         "for filename in os.listdir(Source_QC_folder):\n",
         "  img = imread(os.path.join(Source_QC_folder, filename))\n",
         "  predicted = model_training.predict(img, axes='YX')\n",
-        "  os.chdir(QC_model_path+\"/\"+QC_model_name+\"/Quality Control/Prediction\")\n",
-        "  imsave(filename, predicted)\n",
+        "  imsave(os.path.join(QC_model_path, QC_model_name, \"Quality Control\", \"Prediction\", filename), predicted)\n",
         "\n",
         "\n",
         "def ssim(img1, img2):\n",
@@ -2025,7 +2022,6 @@
         "random_choice = random.choice(os.listdir(Data_folder))\n",
         "x = imread(Data_folder+\"/\"+random_choice)\n",
         "\n",
-        "os.chdir(Result_folder)\n",
         "y = imread(Result_folder+\"/\"+random_choice)\n",
         "\n",
         "plt.figure(figsize=(16,8))\n",
@@ -2095,8 +2091,8 @@
     "accelerator": "GPU",
     "colab": {
       "machine_shape": "hm",
-      "toc_visible": true,
-      "provenance": []
+      "provenance": [],
+      "toc_visible": true
     },
     "kernelspec": {
       "display_name": "Python 3",
@@ -2117,4 +2113,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}
diff --git a/Colab_notebooks/CARE_3D_ZeroCostDL4Mic.ipynb b/Colab_notebooks/CARE_3D_ZeroCostDL4Mic.ipynb
@@ -165,7 +165,7 @@
       "source": [
         "#@markdown ##Install CARE and dependencies\n",
         "!pip uninstall -y -q tensorflow\n",
-        "!pip install -q tensorflow==2.5\n",
+        "!pip install -q tensorflow==2.8\n",
         "\n",
         "import tensorflow \n",
         "\n",
@@ -259,7 +259,7 @@
         "    !pip freeze > $path\n",
         "\n",
         "    # Get minimum requirements file\n",
-        "    df = pd.read_csv(path, delimiter)\n",
+        "    df = pd.read_csv(path)\n",
         "    mod_list = [m.split('.')[0] for m in after if not m in before]\n",
         "    req_list_temp = df.values.tolist()\n",
         "    req_list = [x[0] for x in req_list_temp]\n",
@@ -958,8 +958,6 @@
         "\n",
         "\n",
         "#Load one randomly chosen training target file\n",
-        "\n",
-        "os.chdir(Training_target)\n",
         "y = imread(Training_target+\"/\"+random_choice)\n",
         "\n",
         "f=plt.figure(figsize=(16,8))\n",
@@ -1642,8 +1640,7 @@
         "  img = imread(os.path.join(Source_QC_folder, filename))\n",
         "  n_slices = img.shape[0]\n",
         "  predicted = model_training.predict(img, axes='ZYX', n_tiles=n_tilesZYX)\n",
-        "  os.chdir(path_metrics_save+'Prediction/')\n",
-        "  imsave('Predicted_'+filename, predicted)\n",
+        "  imsave(path_metrics_save+'Prediction/Predicted_'+filename, predicted)\n",
         "\n",
         "\n",
         "def normalize(x, pmin=3, pmax=99.8, axis=None, clip=False, eps=1e-20, dtype=np.float32):\n",

diff --git a/Colab_notebooks/CycleGAN_ZeroCostDL4Mic.ipynb b/Colab_notebooks/CycleGAN_ZeroCostDL4Mic.ipynb