fix: fix typo

app.py

@@ -62,7 +62,7 @@ io_baseline = gr.Interface(frcnn_coco, gr.Image(type="pil"), gr.Image(
     type="file", label="Baseline Model trained on COCO + FT on MOT17"))
 
 io_custom = gr.Interface(frcnn_motsynth, gr.Image(type="pil"), gr.Image(
-    type="pil", label="Faster R-CNN trained on MOTSynth + FT on MOT17"))
+    type="file", label="Faster R-CNN trained on MOTSynth + FT on MOT17"))
 
 gr.Parallel(io_baseline, io_custom, title=title,
             description=description, examples=examples).launch(enable_queue=True)

app.py.7d07da4a5b8438bc3eb3c4039d0839bb.tmp

@@ -1,68 +0,0 @@
-import os.path as osp
-import os
-import gradio as gr
-import torch
-import logging
-import torchvision
-from torchvision.models.detection.faster_rcnn import fasterrcnn_resnet50_fpn
-from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
-from src.detection.graph_utils import add_bbox
-from src.detection.vision import presets
-import torchvision.transforms as T
-
-logging.getLogger('PIL').setLevel(logging.CRITICAL)
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-
-def load_model(baseline: bool = False):
-    if baseline:
-        model = fasterrcnn_resnet50_fpn(
-            weights="DEFAULT")
-    else:
-        model = fasterrcnn_resnet50_fpn()
-        in_features = model.roi_heads.box_predictor.cls_score.in_features
-        model.roi_heads.box_predictor = FastRCNNPredictor(in_features, 2)
-        checkpoint = torch.load(
-            osp.join(os.getcwd(), "model_split3_FT_MOT17.pth"), map_location="cpu")
-        model.load_state_dict(checkpoint["model"])
-    model.to(device)
-    model.eval()
-    return model
-
-
-def frcnn_motsynth(image):
-    model = load_model()
-    transformEval = presets.DetectionPresetEval()
-    image_tensor = transformEval(image, None)[0]
-    image_tensor = image_tensor.to(device)
-    prediction = model([image_tensor])[0]
-    image_w_bbox = add_bbox(image_tensor, prediction, 0.80)
-    torchvision.io.write_png(image_w_bbox, "custom_out.png")
-    return "custom_out.png"
-
-
-def frcnn_coco(image):
-    model = load_model(baseline=True)
-    transformEval = presets.DetectionPresetEval()
-    image_tensor = transformEval(image, None)[0]
-    image_tensor = image_tensor.to(device)
-    prediction = model([image_tensor])[0]
-    image_w_bbox = add_bbox(image_tensor, prediction, 0.80)
-    torchvision.io.write_png(image_w_bbox, "baseline_out.png")
-    return "baseline_out.png"
-
-
-title = "Domain shift adaption on pedestrian detection with Faster R-CNN"
-description = '<p style="text-align:center">School in AI: Deep Learning, Vision and Language for Industry - second edition final project work by Matteo Sirri.</p> '
-examples = ["001.jpg", "002.jpg", "003.jpg",
-            "004.jpg", "005.jpg", "006.jpg", "007.jpg", ]
-
-io_baseline = gr.Interface(frcnn_coco, gr.Image(type="pil"), gr.Image(
-    type="file", label="Baseline Model trained on COCO + FT on MOT17"))
-
-io_custom = gr.Interface(frcnn_motsynth, gr.Image(type="pil"), gr.Image(
-    type="file", label="Faster R-CNN trained on MOTSynth + FT on MOT17"))
-
-gr.Parallel(io_baseline, io_custom, title=title,
-            description=description, examples=examples).launch(enable_queue=True)